{"id":"openenv-2026-07-29","referenceOnly":true,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings","revision":"548f58a232c4aadf05f4798c2d69b8bd95e4b502","author":"Sergio Paniego (@sergiopaniego)","publicationDate":"2026-07-29","runDate":null,"runDateNote":"Not separately published; dataset publication is not a run timestamp.","prompt":"generate an SVG of a pelican riding a bicycle","license":"Apache-2.0","licenseUrl":"/media/collected/2026-10-01-source-backfill/apache-2.0.txt","attributionUrl":"/media/collected/2026-10-01-source-backfill/ATTRIBUTION.txt","envUrl":"https://huggingface.co/spaces/sergiopaniego/pelican-svg-env","repositoryUrl":"https://github.com/huggingface/OpenEnv/tree/main/envs/pelican_svg_env","disclaimer":{"zh":"上游输出，非本馆排名","en":"Upstream outputs, not a Pelican Map ranking"},"rows":[{"id":"zai-org__GLM-5.2__pelican_bicycle__000","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":0,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle while carrying a fish in its beak.","answer_chars":7764,"reasoning_chars":431,"latency_s":39.87,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__000.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__000.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__000.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__000.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-01.png","latency":39.87,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-01-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-01-2026-07-29/","sha256":{"svg":"cf082f1ae76e36237dd84471c1d35aceb404b667c98312e83696c906d8dfcb31","png":"837f7640481e5c27f8f921446ab3a44b6499bf964d77142d60a0e4593fbdf200"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__001","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":1,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird is riding a red bicycle under a sunny sky with clouds.","answer_chars":6948,"reasoning_chars":499,"latency_s":45.56,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__001.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__001.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__001.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__001.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-02.png","latency":45.56,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-02-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-02-2026-07-29/","sha256":{"svg":"9d1cf6050915481d3038461247a8d0c37f7caa59535f20ccec3fba02f6fa6952","png":"18dba30919496070b6b838242dda58edb5601e4fcf5b51659c3b5acd4d1c0e49"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__002","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":2,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a sunny sky with a cloud and a hot dog in its beak.","answer_chars":10757,"reasoning_chars":29561,"latency_s":229.49,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__002.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__002.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__002.svg","localSvg":null,"localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-03.png","latency":229.49,"tags":["benchmark"],"svgDeferredReason":"SVG contains SMIL animation; only the upstream static PNG is displayed for scoring reference.","recordId":"hf-openenv-zai-org-glm-5-2-sample-03-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-03-2026-07-29/","sha256":{"svg":"d13fcefe5a08752f79347198c8f2fa9b4d5cba65fa6c9d2b03aebfb48861d487","png":"621212bb6abb674b171eed944ff576b7027ae53425919c64d3e60954f9423b29"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__003","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":3,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle against a blue sky with clouds.","answer_chars":7923,"reasoning_chars":1209,"latency_s":70.75,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__003.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__003.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__003.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__003.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-04.png","latency":70.75,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-04-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-04-2026-07-29/","sha256":{"svg":"8cec9d1903995e0d7af94f7542d419752bf51e47011dbcf0f2972a0b1d18c9a1","png":"981149984e53e894f6342e388ab227b34fec976459dc3af11d1fde17743b34b6"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__004","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":4,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a bicycle under a sunny sky with clouds.","answer_chars":7196,"reasoning_chars":3847,"latency_s":54.16,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__004.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__004.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__004.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__004.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-05.png","latency":54.16,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-05-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-05-2026-07-29/","sha256":{"svg":"5c1f0dbc040fa7dbcd1b465fc1cd88596525847ec61a8a6d811e921d886a57e3","png":"a041a3ba59ff1fe2066a55f6fbaed424ea09d0f154cca0afc59582b621046dc4"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__005","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":5,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle.","answer_chars":5000,"reasoning_chars":8807,"latency_s":103.07,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__005.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__005.png","structure_score_before_use_fix":0.0,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__005.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__005.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-06.png","latency":103.07,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-06-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-06-2026-07-29/","sha256":{"svg":"b3de7468753f55305535ebcc6122c9515a97ed86aa1b985c31b98b177d91549c","png":"d5e201efaba85e97f239f87211245259a23b254283d71d5e39715b3d1b9853b6"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__006","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":6,"reward":0.9638888888888889,"structure_score":1.0,"semantic_score":0.9444444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican wearing a helmet is riding a red bicycle.","answer_chars":5414,"reasoning_chars":10777,"latency_s":152.65,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__006.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__006.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__006.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__006.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-07.png","latency":152.65,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-07-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-07-2026-07-29/","sha256":{"svg":"cf03aa060f1997930ab5092f2ff077b00b7f9449bb8cb7db44ef0b6868ae6454","png":"5bdc7a12e4d823dc0e6729b0c2bae119d83917e832bdfcb7beef67a1b5244249"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__007","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":7,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with a cloud and sun visible.","answer_chars":6960,"reasoning_chars":7146,"latency_s":122.35,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__007.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__007.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__007.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__007.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-08.png","latency":122.35,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-08-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-08-2026-07-29/","sha256":{"svg":"3a8cf1e59f566caafcf41af5664876a555aedc2eff6a290541b18bd8d6fc99f4","png":"cb5cbb9f2666ecefc1289917591c4ce058e556a13b70ca55efa7cec558e845b0"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__008","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":8,"reward":0.5034722222222222,"structure_score":1.0,"semantic_score":0.2361111111111111,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican with a fish in its beak is riding a red bicycle on a path under a blue sky with clouds.","answer_chars":7500,"reasoning_chars":787,"latency_s":73.73,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__008.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__008.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__008.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__008.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-09.png","latency":73.73,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-09-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-09-2026-07-29/","sha256":{"svg":"60df783a2f0c81a454fa794d72e32f3cd57cc8f6e46617aba5ac21cedf2ce60e","png":"be32e77eed5b9c5f3f845059f0db19dadcfd17171e3d5a98c937ade0f52e95f2"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__009","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":9,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle.","answer_chars":5227,"reasoning_chars":2057,"latency_s":59.7,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__009.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__009.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__009.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__009.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-10.png","latency":59.7,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-10-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-10-2026-07-29/","sha256":{"svg":"b457ef465b52223b732cee4cce757e0bc7a7e482e031498f68f882468ffbc5d9","png":"2d359069a507d2dd00c80723301b1dfea78e5c7241a15e29378c3cbccfa215d5"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__010","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":10,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle on a sandy path under a blue sky with clouds.","answer_chars":7000,"reasoning_chars":712,"latency_s":58.96,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__010.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__010.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__010.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__010.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-11.png","latency":58.96,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-11-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-11-2026-07-29/","sha256":{"svg":"ba06229ac7fa68666ffd790dd095d65b324ddaa9469502f1251f85dd0bcccee6","png":"b655198a8ad0e40fa9133a518040a99f7b799d0b62a9925fecfc54e1148f2e1f"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__011","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":11,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle on a grassy path under a blue sky with clouds.","answer_chars":4975,"reasoning_chars":11828,"latency_s":159.06,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__011.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__011.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__011.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__011.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-12.png","latency":159.06,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-12-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-12-2026-07-29/","sha256":{"svg":"6202d00b2b2e222c6b63bb4e4f406645ae5f3b7af1267d32096d8842dd400772","png":"2180dee3dddb983a590f45543404df8bbedd97ac7d940fca294cc4daafb93a7e"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__012","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":12,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with an orange beak is riding a bicycle.","answer_chars":7353,"reasoning_chars":2069,"latency_s":121.45,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__012.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__012.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__012.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__012.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-13.png","latency":121.45,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-13-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-13-2026-07-29/","sha256":{"svg":"beda47e5c00197b91a788a10df759612349b65043ef4cf9b5d82742ca46f65fc","png":"c2117b10dfc471ddb20354b4b1a1189bd45b5b362e1039ce9bc914763a53d14e"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__013","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":13,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle on a green ground with a blue sky background.","answer_chars":5640,"reasoning_chars":451,"latency_s":87.53,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__013.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__013.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__013.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__013.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-14.png","latency":87.53,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-14-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-14-2026-07-29/","sha256":{"svg":"719a172b4ba9655b740bc659e7b8ec759a7a4beaee6f55e22ac755c7a13bd275","png":"62d9d800a19e12d6cf36ca756e248c32cfcded86f0b04ebf06b8862f855149cd"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__014","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":14,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with clouds.","answer_chars":6571,"reasoning_chars":904,"latency_s":89.78,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__014.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__014.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__014.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__014.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-15.png","latency":89.78,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-15-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-15-2026-07-29/","sha256":{"svg":"a6acbfe00acec402b77b7465e1904d1fc86a32139c2b2628cc4667d71614323c","png":"b054f39d5bd725d0c46dc229f7265f3e402b9317d3c0e40badb20acd9fa686dc"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__015","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":15,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican with a fish in its beak is riding a red bicycle on a road under a blue sky with clouds.","answer_chars":7958,"reasoning_chars":1510,"latency_s":79.98,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__015.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__015.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__015.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__015.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-16.png","latency":79.98,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-16-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-16-2026-07-29/","sha256":{"svg":"b028b42fbd76b851ba891d76b8b3a3947adee4e0e3600e8208f029a60942f286","png":"2d9e2eb00431d7d833b703f86d1fd775b9677fa6914de80c63ebb6f1b7484561"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__016","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":16,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with a yellow beak is riding a red bicycle under a yellow sun.","answer_chars":5393,"reasoning_chars":2975,"latency_s":61.16,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__016.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__016.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__016.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__016.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-17.png","latency":61.16,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-17-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-17-2026-07-29/","sha256":{"svg":"1949bd3da13f6c5745d56c05836e76a2e45e6c67627cfd1c2c4bac814050dbf7","png":"c70244cf7c2562787f4e17947c72534a4d2f686ae81205c55d7305b34774771c"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__017","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":17,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky.","answer_chars":5554,"reasoning_chars":9419,"latency_s":66.9,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__017.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__017.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__017.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__017.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-18.png","latency":66.9,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-18-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-18-2026-07-29/","sha256":{"svg":"bd8aefdc20999c2dd9c7c4127eea1edec85893b43173bf55cc39584766294895","png":"9741b6a1808271555533fdc0a04e3ea5e2626c7c00b5157b7f4912280333cb4f"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__018","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":18,"reward":0.8013888888888889,"structure_score":1.0,"semantic_score":0.6944444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a sunny sky.","answer_chars":5616,"reasoning_chars":10705,"latency_s":69.4,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__018.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__018.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__018.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__018.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-19.png","latency":69.4,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-19-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-19-2026-07-29/","sha256":{"svg":"054254731b226349ad018c0c7cc75a671d46f21b215eba71891f7a7487ae129f","png":"72d02eedc714e485834257bd294d9c1d47824b4bd71e1752bc1a4cd26d03237a"},"mediaStatus":"local"},{"id":"zai-org__GLM-5.2__pelican_bicycle__019","model":"zai-org/GLM-5.2","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":19,"reward":0.8013888888888889,"structure_score":1.0,"semantic_score":0.6944444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle under a blue sky with clouds.","answer_chars":6689,"reasoning_chars":1072,"latency_s":53.86,"svg":"svg/zai-org__GLM-5.2__pelican_bicycle__019.svg","png":"png/zai-org__GLM-5.2__pelican_bicycle__019.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/zai-org__GLM-5.2__pelican_bicycle__019.svg","localSvg":"/media/benchmark/openenv-2026-07-29/zai-org__GLM-5.2__pelican_bicycle__019.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-zai-org-glm-5-2-20.png","latency":53.86,"tags":["benchmark"],"recordId":"hf-openenv-zai-org-glm-5-2-sample-20-2026-07-29","recordPath":"/specimens/hf-openenv-zai-org-glm-5-2-sample-20-2026-07-29/","sha256":{"svg":"94f4e7982bbdfee8b4dff1a38d7fc8fe688e8de21364fef8fc6df9e616090c34","png":"42a2d125a2c7f47b10f41119c0c1bfa8aa8ed9c14cf2e5a254243310941b5c09"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__000","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":0,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on a road under a sunny sky with clouds.","answer_chars":9795,"reasoning_chars":2111,"latency_s":96.22,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__000.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__000.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__000.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__000.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-01.png","latency":96.22,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-01-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-01-2026-07-29/","sha256":{"svg":"df8caa69f7cb039a9300970cc68d8edfb65db5ce88840ea27fd99fb25e4d5580","png":"84c5dcf2b584e4d10ab5cb8e56f8275973697cf1304d2b20f25e54045286f1db"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__001","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":1,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a blue sky with clouds and a sun.","answer_chars":8266,"reasoning_chars":1218,"latency_s":68.88,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__001.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__001.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__001.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__001.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-02.png","latency":68.88,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-02-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-02-2026-07-29/","sha256":{"svg":"6775294b54f0338d7214931598777d1ed0a316c5f20bd7116d133a075ae3df8c","png":"f21afabfda1fd89a32d6fe26d6880bb576dcd290ec409d8f59ddd8420f66d33e"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__002","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":2,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle while holding an orange basket in its beak, with a blue sky, sun, and clouds in the background.","answer_chars":8047,"reasoning_chars":1403,"latency_s":58.97,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__002.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__002.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__002.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__002.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-03.png","latency":58.97,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-03-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-03-2026-07-29/","sha256":{"svg":"b6d8c25d1ff3d4aaf148b8cd6c6a3c73ade031435fe2ed726acb4c9410488776","png":"42dcd79ae0267419314a994d009b68c5e810d7f17a3c62af150e535f565f0ab2"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__003","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":3,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a blue sky with clouds.","answer_chars":7958,"reasoning_chars":1384,"latency_s":104.52,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__003.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__003.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__003.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__003.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-04.png","latency":104.52,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-04-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-04-2026-07-29/","sha256":{"svg":"93f979a9f4446ce6fd56d46662c64fc4bb6404d78f0a69947b4c7e5eb91a8f76","png":"e4ee18d3ae992ae28cb1b41a053f1638b002c21d07d8a42846757f6496f85002"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__004","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":4,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle on a road with clouds in the sky.","answer_chars":9765,"reasoning_chars":1303,"latency_s":68.36,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__004.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__004.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__004.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__004.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-05.png","latency":68.36,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-05-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-05-2026-07-29/","sha256":{"svg":"1ef633eb6be39b2f54035ca5d7cdd7d956573b3c33861c2c529e726b8e5a594a","png":"3cd6f9fd14e7adf935d8b6ef6c8e4524ea5b2742cad5b3859ac7bb24c8221a36"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__005","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":5,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a blue sky with clouds and a sun.","answer_chars":9154,"reasoning_chars":1540,"latency_s":72.08,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__005.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__005.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__005.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__005.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-06.png","latency":72.08,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-06-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-06-2026-07-29/","sha256":{"svg":"7917c1ce3db5c9abf7cacb4fedb1d6acecb17f5ff6582b801da42a9000c61292","png":"92951467a93c4678445a2074ad667501b396df39e4f7bf77419a0735e0c22691"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__006","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":6,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red and black bicycle on a green road with a blue sky background.","answer_chars":8889,"reasoning_chars":1205,"latency_s":116.07,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__006.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__006.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__006.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__006.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-07.png","latency":116.07,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-07-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-07-2026-07-29/","sha256":{"svg":"64faff28fb8e8400f48f31b8f31a29e1e975d2870438f2122e54826ec563d418","png":"a7700a89c3dc4a39b07eb7ca7f463fe453a4a4d6ae163536756b4cff207a1cfd"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__007","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":7,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a sunny blue sky with clouds and grass below.","answer_chars":10714,"reasoning_chars":1371,"latency_s":133.14,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__007.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__007.png","structure_score_before_use_fix":0.8571428571428571,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__007.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__007.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-08.png","latency":133.14,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-08-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-08-2026-07-29/","sha256":{"svg":"c8e4279d0f555ef014f55a289a60e3df6db36ea0341e086c544fc600fd28010a","png":"110b86ff6d18a4e01dc7823993ee145282376054e94138d8eb106e5d1386db39"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__008","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":8,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird is riding a red bicycle with a basket on its back under a sunny sky with clouds.","answer_chars":8911,"reasoning_chars":1402,"latency_s":123.31,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__008.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__008.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__008.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__008.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-09.png","latency":123.31,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-09-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-09-2026-07-29/","sha256":{"svg":"69cc285c90315e7ce20bc0a7cf585e5f32560fd1eb8843d96cf96b32aa21a87e","png":"55729dd1cc75088afecc2ab19d87bb9977de11b1986fd45de3150d492cea129e"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__009","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":9,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a blue sky with clouds and a sun.","answer_chars":8593,"reasoning_chars":1931,"latency_s":65.49,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__009.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__009.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__009.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__009.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-10.png","latency":65.49,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-10-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-10-2026-07-29/","sha256":{"svg":"799e0e5bc213d9eb4661f3abfa0876baeaca9c6c25818983d1ff369d9c0a2332","png":"71f5dcc0d109d9e4e9791efaa0a8745423101eef7410c0547d9a11eebf7566e7"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__010","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":10,"reward":0.45381944444444444,"structure_score":1.0,"semantic_score":0.1597222222222222,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a sunny sky with clouds and grass below.","answer_chars":9889,"reasoning_chars":1082,"latency_s":120.04,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__010.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__010.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__010.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__010.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-11.png","latency":120.04,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-11-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-11-2026-07-29/","sha256":{"svg":"14ea443b88e4a53504b198c018ff173c78daedb77d0077e3beac886e46fa33d4","png":"390929a1641ef6179c56fe57233cb256d9f8bdf8ae503b81e2717fa295c53aa6"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__011","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":11,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle.","answer_chars":3754,"reasoning_chars":13621,"latency_s":105.54,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__011.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__011.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__011.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__011.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-12.png","latency":105.54,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-12-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-12-2026-07-29/","sha256":{"svg":"43f9ade2d3514e9b16f233093705d5e9c2fa210ffc37c3adc9459b785a028635","png":"55924023fd45dc389825faf42d97d3444f9446b95e90013d7f89071225494457"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__012","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":12,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle on grass under a blue sky with clouds and a sun.","answer_chars":9813,"reasoning_chars":1583,"latency_s":97.27,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__012.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__012.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__012.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__012.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-13.png","latency":97.27,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-13-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-13-2026-07-29/","sha256":{"svg":"fe22f6153ac96f5e1690205bd712897709e3e1efeb3966b2d2d3fed3a0a2aad4","png":"a50c6f8fe6da0e8fd775d72143b82eecf5e27209d54ad51e211b8d44c9cff224"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__013","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":13,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on a road under a blue sky with clouds and a sun.","answer_chars":8783,"reasoning_chars":1492,"latency_s":62.11,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__013.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__013.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__013.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__013.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-14.png","latency":62.11,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-14-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-14-2026-07-29/","sha256":{"svg":"c813e97def3b0b96dec42853eb919d7d9396e08f206b9e5d0442aaa9a8c44a9a","png":"3fa40fec67edd6d4e27931287fa51e7817176aac3c594bc2f51d3577fb173a62"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__014","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":14,"reward":0.9638888888888889,"structure_score":1.0,"semantic_score":0.9444444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a blue sky with clouds and a sun.","answer_chars":8960,"reasoning_chars":1201,"latency_s":153.52,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__014.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__014.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__014.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__014.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-15.png","latency":153.52,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-15-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-15-2026-07-29/","sha256":{"svg":"42c4074ae71bd13c1d7c65a4cb7522e7a9a736b00b0799cddd00ab1f5c10e52c","png":"a6e547f40b8187f6f6eceec7342f5c56bd2bb72cf2a2289e8119da1191ae4280"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__015","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":15,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle against a blue sky with clouds.","answer_chars":8251,"reasoning_chars":1198,"latency_s":147.49,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__015.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__015.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__015.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__015.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-16.png","latency":147.49,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-16-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-16-2026-07-29/","sha256":{"svg":"02099608e04c3376038a031f06e65c1bcdd43268f5b8c019e3ca6bea5bf485f4","png":"4cc80a5fa40461b3860ccc543f365af0fa83568426f06671edf9e4ff180a1505"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__016","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":16,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a blue sky with clouds.","answer_chars":9929,"reasoning_chars":866,"latency_s":74.38,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__016.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__016.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__016.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__016.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-17.png","latency":74.38,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-17-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-17-2026-07-29/","sha256":{"svg":"a53993f270438fff738670ba5ba478146376f544f6e5b363454086099fd0ad6d","png":"0e9b7a9db1bc89fb9c6972f4d67983376cfeb68bc6a5ebd803d86e5ab5fca5ce"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__017","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":17,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle on a green ground with a blue sky and clouds in the background.","answer_chars":9099,"reasoning_chars":2208,"latency_s":114.38,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__017.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__017.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__017.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__017.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-18.png","latency":114.38,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-18-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-18-2026-07-29/","sha256":{"svg":"35619d1656a073ce07da1114ed656eec9067b1ebfbb91fbbb57724452eacfbd2","png":"a94df8377a695e9bb12672f2766a47425b0a81879acd916550ccb8a7f54902ae"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__018","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":18,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle on grass under a blue sky with clouds.","answer_chars":8469,"reasoning_chars":1547,"latency_s":63.14,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__018.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__018.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__018.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__018.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-19.png","latency":63.14,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-19-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-19-2026-07-29/","sha256":{"svg":"cc9f825119f348cf8507689c0647bf6fc3849df8fe46fa702481df787efdb798","png":"5f7ce2c030b1b662af87b70fd30a4b59c3b2a169896c3744036a04b4e4cf72e4"},"mediaStatus":"local"},{"id":"Qwen__Qwen3.6-27B__pelican_bicycle__019","model":"Qwen/Qwen3.6-27B","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":19,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle on a green line.","answer_chars":8029,"reasoning_chars":1332,"latency_s":125.1,"svg":"svg/Qwen__Qwen3.6-27B__pelican_bicycle__019.svg","png":"png/Qwen__Qwen3.6-27B__pelican_bicycle__019.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/Qwen__Qwen3.6-27B__pelican_bicycle__019.svg","localSvg":"/media/benchmark/openenv-2026-07-29/Qwen__Qwen3.6-27B__pelican_bicycle__019.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-qwen-qwen3-6-27b-20.png","latency":125.1,"tags":["benchmark"],"recordId":"hf-openenv-qwen-qwen3-6-27b-sample-20-2026-07-29","recordPath":"/specimens/hf-openenv-qwen-qwen3-6-27b-sample-20-2026-07-29/","sha256":{"svg":"213a02c156b303a72936ad35152192385e82c3b4660e4cc922ebbd1ce23ae87c","png":"250717a549fc64c8d7326210be683377ad15731806b361cce1bb8d76ccbbd578"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__000","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":0,"reward":0.8104166666666666,"structure_score":1.0,"semantic_score":0.7083333333333333,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A bird with an orange beak is riding a bicycle with two wheels and handlebars.","answer_chars":3643,"reasoning_chars":1264,"latency_s":268.67,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__000.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__000.png","structure_score_before_use_fix":0.7142857142857143,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__000.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__000.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-01.png","latency":268.67,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-01-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-01-2026-07-29/","sha256":{"svg":"8aee66dff9baa458c9fcbd16f8ad11f1534a8e091c5dc5f74927b39ed554ffbc","png":"e0d1762cbdae11bf890698ca39a0cfc19ef095a0d96cd2d60441f56603f44857"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__001","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":1,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle on a line under a blue sky with a cloud.","answer_chars":5882,"reasoning_chars":1065,"latency_s":31.8,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__001.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__001.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__001.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__001.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-02.png","latency":31.8,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-02-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-02-2026-07-29/","sha256":{"svg":"96f556bba3f20a131d306509ba9989f1ee6238c6b690fc130c0017dd8f8a045f","png":"9689fb8fe38b047012899ae85d220648e3aba757b134166927a293765660dc05"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__002","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":2,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle.","answer_chars":5665,"reasoning_chars":913,"latency_s":68.4,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__002.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__002.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__002.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__002.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-03.png","latency":68.4,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-03-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-03-2026-07-29/","sha256":{"svg":"85b28a88fccba4244eb4d0dccb2987e5903ca77e8dd21441aefda2ce82ddc0bc","png":"4adedd603a261be86ea5a8bca2a4f6c1af7a58a97280df6efc61ac7ee3bb18cd"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__003","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":3,"reward":0.46510416666666665,"structure_score":1.0,"semantic_score":0.17708333333333331,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with an orange beak and feet is riding a bicycle with two large wheels.","answer_chars":3533,"reasoning_chars":3561,"latency_s":35.8,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__003.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__003.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__003.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__003.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-04.png","latency":35.8,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-04-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-04-2026-07-29/","sha256":{"svg":"cf89e41036cd3cb273f413b9ab43b632e020b754d5f43ee8e1125ec48528ed52","png":"f0c1b794611f906e1d9be5471f77854736b32b7b4f0fc9915a380db14df03801"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__004","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":4,"reward":0.8465277777777778,"structure_score":1.0,"semantic_score":0.7638888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"The image shows a cartoon-style drawing of a white bird with an orange beak riding a bicycle.","answer_chars":4285,"reasoning_chars":2377,"latency_s":69.25,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__004.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__004.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__004.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__004.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-05.png","latency":69.25,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-05-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-05-2026-07-29/","sha256":{"svg":"241e1b82a29aeaddff6805e9b985fcaba8c157192e294666098a95af18e829e6","png":"c224591193730bd13c1343ab9ab28b603acc3992e05b9b6dfa5a17b198df1184"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__005","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":5,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A stick figure with an orange beak is riding a bicycle.","answer_chars":1745,"reasoning_chars":3677,"latency_s":28.18,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__005.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__005.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__005.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__005.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-06.png","latency":28.18,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-06-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-06-2026-07-29/","sha256":{"svg":"48fb5dd0a36543540a606115936087b97096d90a9b5a6d49a11963a1e65d0261","png":"14cc04ed84d0d1156e00e22122ef81edf9b21fa97d6cb4b2eee3cc0706651283"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__006","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":6,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a bicycle under a sunny sky with clouds.","answer_chars":7919,"reasoning_chars":1089,"latency_s":24.75,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__006.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__006.png","structure_score_before_use_fix":0.7142857142857143,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__006.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__006.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-07.png","latency":24.75,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-07-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-07-2026-07-29/","sha256":{"svg":"634e99a64d51926d24c641d91919f6ff7c541fc18746493082e36b6fb9c7f50b","png":"1d89255d7251eab2bcc726322d5184431c9cceed35aadaaed05df60d50069ee6"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__007","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":7,"reward":0.8465277777777778,"structure_score":1.0,"semantic_score":0.7638888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A bird with an orange beak is riding a bicycle.","answer_chars":5159,"reasoning_chars":3550,"latency_s":101.63,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__007.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__007.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__007.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__007.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-08.png","latency":101.63,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-08-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-08-2026-07-29/","sha256":{"svg":"a3b8992a7f2049094d92e0bcda683fe567729e73562cd7aabcefde922bddd5f0","png":"d3b46d136eeb8c6b773a3b2d5a3a9ba82ed48102208b1a3b7ae6565dd6583932"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__008","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":8,"reward":0.8013888888888889,"structure_score":1.0,"semantic_score":0.6944444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a bicycle.","answer_chars":4953,"reasoning_chars":1481,"latency_s":12.76,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__008.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__008.png","structure_score_before_use_fix":0.7142857142857143,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__008.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__008.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-09.png","latency":12.76,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-09-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-09-2026-07-29/","sha256":{"svg":"57cadf38b5e1fd0983a07ccfb4f713bebcda171d1aab4d0b413ec63bee394f5a","png":"69e733b31d529835b5df5a9a2727246bc13f37728fac6cfddbd74dd909265b66"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__009","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":9,"reward":0.95,"structure_score":0.8571428571428571,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle.","answer_chars":4787,"reasoning_chars":1164,"latency_s":10.91,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__009.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__009.png","structure_score_before_use_fix":0.7142857142857143,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__009.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__009.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-10.png","latency":10.91,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-10-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-10-2026-07-29/","sha256":{"svg":"f4ce6c9053e05d27b32394fae59378a6c6430436ba3c2b33964bbd3dbc1299a9","png":"56780fa0cd593b8f05628f9bb6a8eb6220494cc9bd74a90f689dea051393d673"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__010","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":10,"reward":0.4944444444444444,"structure_score":1.0,"semantic_score":0.2222222222222222,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"The image shows a bicycle with a pelican perched on its frame.","answer_chars":4549,"reasoning_chars":961,"latency_s":16.29,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__010.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__010.png","structure_score_before_use_fix":0.8571428571428571,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__010.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__010.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-11.png","latency":16.29,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-11-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-11-2026-07-29/","sha256":{"svg":"7780e810abc6b3c579a42490f2c22e748a4cbf816db831fbf68fb29d004ea77d","png":"2518269ad6388d0c03413d3e782214bfe4af7909adb407c631344f5d103d69d9"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__011","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":11,"reward":0.8826388888888889,"structure_score":1.0,"semantic_score":0.8194444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A bird with an orange beak is riding a bicycle while holding a paper airplane in its beak.","answer_chars":3635,"reasoning_chars":1035,"latency_s":22.6,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__011.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__011.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__011.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__011.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-12.png","latency":22.6,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-12-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-12-2026-07-29/","sha256":{"svg":"e5177aa93b87de3f45a43a8fba333cfa988b8171013dd6067823df62d5007da1","png":"4b94bbbd70ebf655ee94157d999525bdcb69bc2cda090c230537f224895f9056"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__012","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":12,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"The image depicts a stylized drawing of a bicycle with a large, rounded front and two wheels, but the rider is not clearly identifiable.","answer_chars":4940,"reasoning_chars":1250,"latency_s":10.56,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__012.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__012.png","structure_score_before_use_fix":0.7142857142857143,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__012.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__012.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-13.png","latency":10.56,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-13-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-13-2026-07-29/","sha256":{"svg":"d2a164eb732df48bb656e085720cf93f1885aaff98f91c26bee44303f33a96d4","png":"a048f08a1f4c75b33964612f4d6c6de5e2d37ebf8e0237aa529b2fbf1b01e17a"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__013","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":13,"reward":0.913888888888889,"structure_score":0.8571428571428571,"semantic_score":0.9444444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle with its wings spread out.","answer_chars":6103,"reasoning_chars":1062,"latency_s":129.18,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__013.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__013.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__013.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__013.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-14.png","latency":129.18,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-14-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-14-2026-07-29/","sha256":{"svg":"f1f026a603793378cb2ec11d936c3f5151f97b7a911678b06e303f0412a1864d","png":"020c29dddef13fc565615c4401a298c0ad0386689e470edf8c0c05b370ca2dad"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__014","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":14,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle.","answer_chars":3598,"reasoning_chars":1363,"latency_s":21.0,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__014.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__014.png","structure_score_before_use_fix":0.8571428571428571,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__014.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__014.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-15.png","latency":21.0,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-15-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-15-2026-07-29/","sha256":{"svg":"92e5141eaa5736e5d69703e9e7af7bd70edfd60175e87171c3de6c3b065405e1","png":"dd0f2a0281b7e50b3e92ff19a9d716a74d611027b1e1a8a0c5644104fd1cd11b"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__015","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":15,"reward":0.4560763888888889,"structure_score":1.0,"semantic_score":0.16319444444444445,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A bicycle with orange arrows pointing at its pedals and handlebars, and a bird-like figure above it.","answer_chars":3530,"reasoning_chars":2492,"latency_s":296.77,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__015.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__015.png","structure_score_before_use_fix":0.8571428571428571,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__015.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__015.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-16.png","latency":296.77,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-16-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-16-2026-07-29/","sha256":{"svg":"dcf47fd79d6fc80b535f0e95caa1a6d4b5c566998c24fbf007e1d5ac4d2aac31","png":"88a65bc5f404ed6768f0abb19008d0cde0fe1d702122b34df193afdb5db60482"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__016","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":16,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a bicycle.","answer_chars":4713,"reasoning_chars":2796,"latency_s":16.48,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__016.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__016.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__016.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__016.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-17.png","latency":16.48,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-17-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-17-2026-07-29/","sha256":{"svg":"4dd020d40fc422634bc0908e2ebe095ec31ec772f3b0d439583fd44427e012a6","png":"fbd4bf40f666fd52f6ac7c43c9c833807e3daac21de8fd43d8e05b4dff660a20"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__017","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":17,"reward":0.9638888888888889,"structure_score":1.0,"semantic_score":0.9444444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle with large wheels on a grassy area against a light blue background.","answer_chars":5576,"reasoning_chars":1118,"latency_s":24.27,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__017.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__017.png","structure_score_before_use_fix":0.8571428571428571,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__017.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__017.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-18.png","latency":24.27,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-18-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-18-2026-07-29/","sha256":{"svg":"e80be8926de9d3f9100f3123ac09ca9f1fa6cc46a0691e9e900b104e91f1b11f","png":"c9b21067165ba7271905f3339fe0062a2e6ed2297603e086c1562df122aab35f"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__018","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":18,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle on a line.","answer_chars":5171,"reasoning_chars":867,"latency_s":17.09,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__018.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__018.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__018.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__018.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-19.png","latency":17.09,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-19-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-19-2026-07-29/","sha256":{"svg":"323c1c77bbbc3656d6e158f4f10269e58acf76f59416a7a075080d79bdbbb74a","png":"1521f488d99ab6b269edaf055e0d5063b87cfa5e439be4a2c4028958b97d802c"},"mediaStatus":"local"},{"id":"nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__019","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":19,"reward":0.8104166666666666,"structure_score":1.0,"semantic_score":0.7083333333333333,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with an orange beak is riding a bicycle.","answer_chars":2071,"reasoning_chars":2121,"latency_s":10.86,"svg":"svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__019.svg","png":"png/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__019.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__019.svg","localSvg":"/media/benchmark/openenv-2026-07-29/nvidia__NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4__pelican_bicycle__019.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-20.png","latency":10.86,"tags":["benchmark"],"recordId":"hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-20-2026-07-29","recordPath":"/specimens/hf-openenv-nvidia-nvidia-nemotron-3-ultra-550b-a55b-nvfp4-sample-20-2026-07-29/","sha256":{"svg":"0783008647cc020f0e9f4c98d75b6b14bb95fbd9f72566445b14149610b76110","png":"e85d2678b30d102d566c9bafc8f57fc9ff802256c6db70f9e474793e7a7f8752"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__000","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":0,"reward":0.8013888888888889,"structure_score":1.0,"semantic_score":0.6944444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle.","answer_chars":3862,"reasoning_chars":0,"latency_s":24.25,"svg":"svg/claude-fable-5__pelican_bicycle__000.svg","png":"png/claude-fable-5__pelican_bicycle__000.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__000.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__000.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-01.png","latency":24.25,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-01-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-01-2026-07-29/","sha256":{"svg":"c21a20d95a4ef5e2f379917bc963d7b42a7e86687005871a937322e8889dfd5f","png":"1c7096b60619863b10500f556c0d7ab8c4156caa00e64323ca20f0a6595bacf2"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__001","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":1,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle under a yellow sun.","answer_chars":3692,"reasoning_chars":0,"latency_s":22.41,"svg":"svg/claude-fable-5__pelican_bicycle__001.svg","png":"png/claude-fable-5__pelican_bicycle__001.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__001.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__001.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-02.png","latency":22.41,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-02-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-02-2026-07-29/","sha256":{"svg":"e6f10c166b7cfc1800108b8eb342479b48037c9262651b1f0cb3840a9f5ebf12","png":"5719432f4d8e21662e638396bfbc5d197b7e399a17e5202a5b65682680740769"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__002","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":2,"reward":0.8826388888888889,"structure_score":1.0,"semantic_score":0.8194444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird is riding a red bicycle while holding a yellow object in its beak.","answer_chars":3539,"reasoning_chars":0,"latency_s":23.06,"svg":"svg/claude-fable-5__pelican_bicycle__002.svg","png":"png/claude-fable-5__pelican_bicycle__002.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__002.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__002.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-03.png","latency":23.06,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-03-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-03-2026-07-29/","sha256":{"svg":"34959e92158c54acab75b2bd59e38a27fd105ea5b6f2fa4afb5e3a4d303a0566","png":"79c2dc27921c2e8442232ec35749568557e7f75d60a680c8db43b98984bfdbd5"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__003","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":3,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle under a yellow sun.","answer_chars":3760,"reasoning_chars":0,"latency_s":23.58,"svg":"svg/claude-fable-5__pelican_bicycle__003.svg","png":"png/claude-fable-5__pelican_bicycle__003.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__003.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__003.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-04.png","latency":23.58,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-04-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-04-2026-07-29/","sha256":{"svg":"a9ff73eec8d2dfe36541b10fb30263f93cf3b93e215fef2bf679844705860538","png":"09a8ac3abf36c0930b4bc23ade2b5b949d619dcb6664beabe6bc78d0e1c7fb68"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__004","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":4,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle under a yellow sun.","answer_chars":3793,"reasoning_chars":0,"latency_s":29.07,"svg":"svg/claude-fable-5__pelican_bicycle__004.svg","png":"png/claude-fable-5__pelican_bicycle__004.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__004.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__004.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-05.png","latency":29.07,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-05-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-05-2026-07-29/","sha256":{"svg":"1e99154fa4333193e0bcc024ebde8bf0884d91f0e4b9bcd427113e5177dcd431","png":"7b4bf9c1a611b2853cc271501d2031e6de827da9a38c2a91d34c5ca42997bdb9"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__005","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":5,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle and holding a yellow ball in its beak.","answer_chars":3288,"reasoning_chars":0,"latency_s":21.39,"svg":"svg/claude-fable-5__pelican_bicycle__005.svg","png":"png/claude-fable-5__pelican_bicycle__005.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__005.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__005.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-06.png","latency":21.39,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-06-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-06-2026-07-29/","sha256":{"svg":"7b1fcaf0525136d93d6eb2537e30031522ecba78813ee25ecfd12127307f6634","png":"48c529507f67eb4205feecffb4b24a0e019f96a006c79b9b8de0640b49ad56cf"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__006","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":6,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle under a yellow sun.","answer_chars":3257,"reasoning_chars":0,"latency_s":21.21,"svg":"svg/claude-fable-5__pelican_bicycle__006.svg","png":"png/claude-fable-5__pelican_bicycle__006.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__006.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__006.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-07.png","latency":21.21,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-07-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-07-2026-07-29/","sha256":{"svg":"fcd57a60f43346d568b3134c2936cc47c394856bce2130f5022c2e016169ddb3","png":"6cdadd9081b7e8631fc3afe7d32f9fcd95bc6447b0784b41bc6087469d303f89"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__007","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":7,"reward":0.8013888888888889,"structure_score":1.0,"semantic_score":0.6944444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle on a green surface against a light blue background.","answer_chars":3785,"reasoning_chars":0,"latency_s":23.51,"svg":"svg/claude-fable-5__pelican_bicycle__007.svg","png":"png/claude-fable-5__pelican_bicycle__007.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__007.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__007.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-08.png","latency":23.51,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-08-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-08-2026-07-29/","sha256":{"svg":"62c78819f59b5c379bb7ae0d658ff69548405a7e04d29438e8952b76bfc20eb2","png":"0fc24a3559738a03b34cc48d355fbac7b7e91a44195a2956f38c35d956181dbe"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__008","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":8,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle.","answer_chars":3886,"reasoning_chars":0,"latency_s":25.99,"svg":"svg/claude-fable-5__pelican_bicycle__008.svg","png":"png/claude-fable-5__pelican_bicycle__008.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__008.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__008.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-09.png","latency":25.99,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-09-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-09-2026-07-29/","sha256":{"svg":"51877843b0f1e78a93ffb39da14107619ed43ed5012591fef451373f37575db8","png":"4160ac3790538219f546c02bac667ad1e580dc1b0b5d50bef9cf500d474824eb"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__009","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":9,"reward":0.8013888888888889,"structure_score":1.0,"semantic_score":0.6944444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle under a yellow sun.","answer_chars":3845,"reasoning_chars":0,"latency_s":24.52,"svg":"svg/claude-fable-5__pelican_bicycle__009.svg","png":"png/claude-fable-5__pelican_bicycle__009.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__009.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__009.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-10.png","latency":24.52,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-10-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-10-2026-07-29/","sha256":{"svg":"dc7b19d9f89c0e59d0d1949d7160ecc5fd0cdb33513b69900877ae14d1ccb390","png":"b5a919ec295a937c520d6b8df7b08c026a78a52e8bcd37c376e5d5166455bacd"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__010","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":10,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird is riding a red bicycle under a sunny sky.","answer_chars":3977,"reasoning_chars":0,"latency_s":27.41,"svg":"svg/claude-fable-5__pelican_bicycle__010.svg","png":"png/claude-fable-5__pelican_bicycle__010.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__010.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__010.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-11.png","latency":27.41,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-11-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-11-2026-07-29/","sha256":{"svg":"1886bc188dab746f739b2d461366e9d1369e42e7b673c3b43aa02b6a4bcaa39c","png":"078ecf58ae948b03217509ff74325cbc673eb73c4dd74cbf8f93ad5342e35d50"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__011","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":11,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a sunny sky with a cloud and sun visible.","answer_chars":4026,"reasoning_chars":0,"latency_s":25.02,"svg":"svg/claude-fable-5__pelican_bicycle__011.svg","png":"png/claude-fable-5__pelican_bicycle__011.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__011.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__011.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-12.png","latency":25.02,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-12-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-12-2026-07-29/","sha256":{"svg":"8d5fdce1ab68f966975b5cd70189510d94b5779d93393568907e79580e0bb5ec","png":"0dafd90fbce199ec118a438aa2fdd4615148f1ba40e75faf598980ee1eabecfd"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__012","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":12,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle.","answer_chars":3644,"reasoning_chars":0,"latency_s":24.18,"svg":"svg/claude-fable-5__pelican_bicycle__012.svg","png":"png/claude-fable-5__pelican_bicycle__012.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__012.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__012.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-13.png","latency":24.18,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-13-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-13-2026-07-29/","sha256":{"svg":"0caf30803b8880c31b92cb5684f4ad3d68be482457700b72aab3374e9f0df4df","png":"b09fb8e5ba18693776df3e762c69a262cd8de07ab53e49d3795f14f5e912d5d7"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__013","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":13,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle.","answer_chars":3815,"reasoning_chars":0,"latency_s":24.2,"svg":"svg/claude-fable-5__pelican_bicycle__013.svg","png":"png/claude-fable-5__pelican_bicycle__013.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__013.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__013.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-14.png","latency":24.2,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-14-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-14-2026-07-29/","sha256":{"svg":"52c116f9cd0a69e899f3d7376087560a4fb45e4b8030a2546f46fa852952670c","png":"82dc2c9e3870be31d67c9bf90048bf38f9640e7f943544ca95a77c1179106a34"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__014","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":14,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle.","answer_chars":3780,"reasoning_chars":0,"latency_s":23.77,"svg":"svg/claude-fable-5__pelican_bicycle__014.svg","png":"png/claude-fable-5__pelican_bicycle__014.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__014.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__014.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-15.png","latency":23.77,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-15-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-15-2026-07-29/","sha256":{"svg":"68864357353588334997cebb06d4d79a4777ada0b5bdff4ef51e539184857eb7","png":"97e9bda394d99655a09b565896d01e3c72cdc98ce91a8fc6363df9e1e89d0200"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__015","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":15,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle with a yellow sun in the background.","answer_chars":3807,"reasoning_chars":0,"latency_s":24.83,"svg":"svg/claude-fable-5__pelican_bicycle__015.svg","png":"png/claude-fable-5__pelican_bicycle__015.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__015.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__015.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-16.png","latency":24.83,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-16-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-16-2026-07-29/","sha256":{"svg":"d94bd1481f550e5413269b3a815d0cbe8c4b85ef4a2dcc303961fe5d9211eaa3","png":"e7db862ccda597e4e1d24a4773980c9d68fa1375496b0181d958ffef8152ab5e"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__016","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":16,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird is riding a red bicycle under a yellow sun.","answer_chars":3418,"reasoning_chars":0,"latency_s":22.24,"svg":"svg/claude-fable-5__pelican_bicycle__016.svg","png":"png/claude-fable-5__pelican_bicycle__016.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__016.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__016.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-17.png","latency":22.24,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-17-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-17-2026-07-29/","sha256":{"svg":"cf47bba4764d3e0a3bebf3e008af516d999376ab67666f7a202c137b8bb41ca3","png":"da72269b60ae968f8cdd0de9022f29d379c8774adaea0c8a868c534d0d8de0a7"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__017","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":17,"reward":0.8465277777777778,"structure_score":1.0,"semantic_score":0.7638888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird is riding a red bicycle under a yellow sun.","answer_chars":3910,"reasoning_chars":0,"latency_s":24.78,"svg":"svg/claude-fable-5__pelican_bicycle__017.svg","png":"png/claude-fable-5__pelican_bicycle__017.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__017.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__017.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-18.png","latency":24.78,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-18-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-18-2026-07-29/","sha256":{"svg":"90ad326064fe93b5566c957730a629672abd3b5dde49f80c6b27137b5cbd0aff","png":"d325809b0d927da98bb9994399598b386eb4436a997d8ab23215691994ba26b4"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__018","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":18,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle.","answer_chars":3659,"reasoning_chars":0,"latency_s":22.62,"svg":"svg/claude-fable-5__pelican_bicycle__018.svg","png":"png/claude-fable-5__pelican_bicycle__018.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__018.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__018.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-19.png","latency":22.62,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-19-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-19-2026-07-29/","sha256":{"svg":"878e397b62d1f2296d55b1214c2f9721af65c764bf7b4ef544d30e01190250ae","png":"a82a2393f46d9f0dd1cb9aea5e1e745b2689b0b657c59bd867ba9537245fea5c"},"mediaStatus":"local"},{"id":"claude-fable-5__pelican_bicycle__019","model":"claude-fable-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":19,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird is riding a red bicycle under a yellow sun.","answer_chars":3402,"reasoning_chars":0,"latency_s":27.39,"svg":"svg/claude-fable-5__pelican_bicycle__019.svg","png":"png/claude-fable-5__pelican_bicycle__019.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-fable-5__pelican_bicycle__019.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-fable-5__pelican_bicycle__019.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-fable-5-20.png","latency":27.39,"tags":["benchmark"],"recordId":"hf-openenv-claude-fable-5-sample-20-2026-07-29","recordPath":"/specimens/hf-openenv-claude-fable-5-sample-20-2026-07-29/","sha256":{"svg":"e7fa8a84e9feb32032bf3c5c7a43415d64596915133603e7353570b34ba65c93","png":"8786a6709cde75553a50774730658c093271e9f07e3ef27c6e24f92217e8b87d"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__000","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":0,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle on a green ground with a blue sky and clouds in the background.","answer_chars":3995,"reasoning_chars":0,"latency_s":44.02,"svg":"svg/claude-opus-5__pelican_bicycle__000.svg","png":"png/claude-opus-5__pelican_bicycle__000.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__000.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__000.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-01.png","latency":44.02,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-01-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-01-2026-07-29/","sha256":{"svg":"86c8232ba977347dca5f053e9230dedab52dbfbbfcc8817c13af4881f4c52768","png":"4f9d870639dff84b027fad17fdf4ef2db6a7f92cea947feabd83a518feb6a910"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__001","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":1,"reward":0.7652777777777777,"structure_score":1.0,"semantic_score":0.6388888888888888,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose with an orange beak and legs is riding a red bicycle.","answer_chars":4164,"reasoning_chars":0,"latency_s":27.42,"svg":"svg/claude-opus-5__pelican_bicycle__001.svg","png":"png/claude-opus-5__pelican_bicycle__001.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__001.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__001.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-02.png","latency":27.42,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-02-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-02-2026-07-29/","sha256":{"svg":"0c0e1c7a6584ffa0de3d00d1d6e66ea8336199aedba0a963b01fa9a4647bc08a","png":"e329e4047670253d72b4d49fd1ac08b770928ecb8f593eab255d962243642499"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__002","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":2,"reward":0.4944444444444444,"structure_score":1.0,"semantic_score":0.2222222222222222,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red and yellow bicycle.","answer_chars":3963,"reasoning_chars":0,"latency_s":43.9,"svg":"svg/claude-opus-5__pelican_bicycle__002.svg","png":"png/claude-opus-5__pelican_bicycle__002.png","structure_score_before_use_fix":0.14285714285714285,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__002.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__002.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-03.png","latency":43.9,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-03-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-03-2026-07-29/","sha256":{"svg":"7ec6922170255b59dc0fd79a363a989393ce4ebdfbe6c3e65eb96dfef0cf1f94","png":"585dc50e59e5f60760a4e8960d610b776a68b8487bef6cd2344d74cdf9345875"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__003","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":3,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck wearing a red scarf is riding a red bicycle.","answer_chars":4127,"reasoning_chars":0,"latency_s":28.36,"svg":"svg/claude-opus-5__pelican_bicycle__003.svg","png":"png/claude-opus-5__pelican_bicycle__003.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__003.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__003.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-04.png","latency":28.36,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-04-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-04-2026-07-29/","sha256":{"svg":"8d1b48abd3feff12f1f4a258a0a874bab7e83314b8dfa1f8e49663986840c289","png":"f836e895a043277f9eff702cffd48459ee976452b148fc92487dfc08670804e2"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__004","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":4,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle.","answer_chars":4336,"reasoning_chars":0,"latency_s":40.06,"svg":"svg/claude-opus-5__pelican_bicycle__004.svg","png":"png/claude-opus-5__pelican_bicycle__004.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__004.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__004.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-05.png","latency":40.06,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-05-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-05-2026-07-29/","sha256":{"svg":"e79099b0e20826bafb1125260651f2185958d86fd5b3a188ad7e4a7bbbdd6d4c","png":"7bf0bd9cecf9438c23510267eee5aca307b2d6d20d82646514d5b33fe5ecaadb"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__005","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":5,"reward":0.8013888888888889,"structure_score":1.0,"semantic_score":0.6944444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle.","answer_chars":4371,"reasoning_chars":0,"latency_s":47.29,"svg":"svg/claude-opus-5__pelican_bicycle__005.svg","png":"png/claude-opus-5__pelican_bicycle__005.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__005.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__005.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-06.png","latency":47.29,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-06-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-06-2026-07-29/","sha256":{"svg":"19d71e8c1041938d7f772381e514dc032c26ac3cd0494608e9e3ccb8aa6709b6","png":"451370bdeeabd5dd7c18f214a01c297c91139f1962a496bf0287d46bac929a15"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__006","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":6,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle with its wings outstretched, and there is a yellow circle resembling the sun in the background.","answer_chars":3887,"reasoning_chars":0,"latency_s":51.91,"svg":"svg/claude-opus-5__pelican_bicycle__006.svg","png":"png/claude-opus-5__pelican_bicycle__006.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__006.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__006.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-07.png","latency":51.91,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-07-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-07-2026-07-29/","sha256":{"svg":"c853c5d04c51fe2afae953bb8b2c4f453c92a0e14dfabdfabeb9f5084ec017c9","png":"661aebf3f6504d56e65f6c5f62cd0897cb52d1a94c2ebd5a875b41841382524c"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__007","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":7,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle.","answer_chars":4379,"reasoning_chars":0,"latency_s":43.12,"svg":"svg/claude-opus-5__pelican_bicycle__007.svg","png":"png/claude-opus-5__pelican_bicycle__007.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__007.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__007.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-08.png","latency":43.12,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-08-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-08-2026-07-29/","sha256":{"svg":"08ad930d9efaa8efdc847503ab277b7fdc05772862a8f5adc64fbc7c8aec1b89","png":"50b107cf79f7cd8392b3866f0cb6763eda669a5d284318ef60c9a2d11638a311"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__008","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":8,"reward":0.8826388888888889,"structure_score":1.0,"semantic_score":0.8194444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with an orange beak is riding a red bicycle against a light blue background.","answer_chars":3895,"reasoning_chars":0,"latency_s":25.03,"svg":"svg/claude-opus-5__pelican_bicycle__008.svg","png":"png/claude-opus-5__pelican_bicycle__008.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__008.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__008.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-09.png","latency":25.03,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-09-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-09-2026-07-29/","sha256":{"svg":"d2fa5470731266c59486be57296fe71b199e44fbcf497bf187ba69014d05d759","png":"87123d55b54c8d297530426f1088b74ee12ce5c7fb8dddca75a42cad561beaf1"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__009","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":9,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle.","answer_chars":3603,"reasoning_chars":0,"latency_s":36.72,"svg":"svg/claude-opus-5__pelican_bicycle__009.svg","png":"png/claude-opus-5__pelican_bicycle__009.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__009.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__009.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-10.png","latency":36.72,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-10-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-10-2026-07-29/","sha256":{"svg":"a3a0ce2595ea3b635b47aef5fb360292a098cd4f7ca6604ddefca211ed9e503b","png":"e6c74a2fe5ee348071b0b8d0693ccccbe932d1698bc4a40d418427b82b174714"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__010","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":10,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose is riding a red bicycle.","answer_chars":4487,"reasoning_chars":0,"latency_s":35.34,"svg":"svg/claude-opus-5__pelican_bicycle__010.svg","png":"png/claude-opus-5__pelican_bicycle__010.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__010.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__010.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-11.png","latency":35.34,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-11-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-11-2026-07-29/","sha256":{"svg":"2083fac9635b1b3b035566fbc27e375f05b6b1179c635b622f3d88eb04de7203","png":"a69e81cd1ff2e10cd4df454f49dc87f5c216bd8c7a6aaa85d6fa77c7e5f18ff9"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__011","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":11,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle.","answer_chars":3978,"reasoning_chars":0,"latency_s":27.42,"svg":"svg/claude-opus-5__pelican_bicycle__011.svg","png":"png/claude-opus-5__pelican_bicycle__011.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__011.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__011.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-12.png","latency":27.42,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-12-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-12-2026-07-29/","sha256":{"svg":"740b6066873476b2be5906976ffb64fa74b9002a348ce86478ae97be090ce9c3","png":"b070ee51416c6f6387134272e10ede855e61dace07c1a19ec38020f9c22feb9a"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__012","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":12,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose with an orange beak is riding a bicycle.","answer_chars":3362,"reasoning_chars":0,"latency_s":23.64,"svg":"svg/claude-opus-5__pelican_bicycle__012.svg","png":"png/claude-opus-5__pelican_bicycle__012.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__012.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__012.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-13.png","latency":23.64,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-13-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-13-2026-07-29/","sha256":{"svg":"1e07ea9f3fcf80598de90af6cec90b33af999e67c881f46d122302b6e025dbf4","png":"d74243f476f31b04513cf0cf5c0f61a099c038c3df2dece1bc00b2c213d8a8a8"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__013","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":13,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle.","answer_chars":4045,"reasoning_chars":0,"latency_s":36.71,"svg":"svg/claude-opus-5__pelican_bicycle__013.svg","png":"png/claude-opus-5__pelican_bicycle__013.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__013.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__013.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-14.png","latency":36.71,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-14-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-14-2026-07-29/","sha256":{"svg":"34f116ca96cbc9f014bfd3524998e708216e1f6c315c3af900af615b1393b3d5","png":"92625f32916989f1aedcc96bce8173be05071b09557443cd617c01fdea8fad9c"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__014","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":14,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle.","answer_chars":4095,"reasoning_chars":0,"latency_s":36.04,"svg":"svg/claude-opus-5__pelican_bicycle__014.svg","png":"png/claude-opus-5__pelican_bicycle__014.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__014.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__014.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-15.png","latency":36.04,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-15-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-15-2026-07-29/","sha256":{"svg":"e7718ce90d125499982b15c9e572a05c3eb9a17e869474f1aa58c1162e0076ff","png":"9a3065c14d97fc265d542f36cd89786c8cb36a31795b2838278dca972e36a51e"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__015","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":15,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle.","answer_chars":3656,"reasoning_chars":0,"latency_s":35.08,"svg":"svg/claude-opus-5__pelican_bicycle__015.svg","png":"png/claude-opus-5__pelican_bicycle__015.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__015.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__015.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-16.png","latency":35.08,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-16-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-16-2026-07-29/","sha256":{"svg":"e97a9b77579a3a5234f8f53c086230e9938878f96ed61858e9b12c90e82fa7af","png":"0faab311b3fa4fd61ae0412a95761605a49178a4976a6e861ea29713cf82a098"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__016","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":16,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle.","answer_chars":3222,"reasoning_chars":0,"latency_s":33.39,"svg":"svg/claude-opus-5__pelican_bicycle__016.svg","png":"png/claude-opus-5__pelican_bicycle__016.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__016.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__016.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-17.png","latency":33.39,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-17-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-17-2026-07-29/","sha256":{"svg":"c5a245256db13fa030d57713065075b874fda18089fd1e4c91e88365475707b8","png":"26dea4b7dfd940438dbb8dae4f207a8be8125e0067f970aac80e28047609282f"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__017","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":17,"reward":0.8826388888888889,"structure_score":1.0,"semantic_score":0.8194444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with an orange beak is riding a bicycle.","answer_chars":4016,"reasoning_chars":0,"latency_s":37.33,"svg":"svg/claude-opus-5__pelican_bicycle__017.svg","png":"png/claude-opus-5__pelican_bicycle__017.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__017.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__017.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-18.png","latency":37.33,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-18-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-18-2026-07-29/","sha256":{"svg":"c271ab65ed51cd996d13c9fa1436b22d6e81b907b5666b77be8440efac9438f1","png":"66d984bd910c636c486143568090039c0b2fe2aac4211049208b048c6e68a9c7"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__018","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":18,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a bicycle.","answer_chars":4671,"reasoning_chars":0,"latency_s":49.62,"svg":"svg/claude-opus-5__pelican_bicycle__018.svg","png":"png/claude-opus-5__pelican_bicycle__018.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__018.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__018.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-19.png","latency":49.62,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-19-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-19-2026-07-29/","sha256":{"svg":"66b0a2c2337a8dbed483d5e0808da28702b6f0b76d8ffffd65b81897d28d19d5","png":"e419556fb0e3295553006810cbd5f4b7c60846400e6bef825f37c1e4bbe89f83"},"mediaStatus":"local"},{"id":"claude-opus-5__pelican_bicycle__019","model":"claude-opus-5","access":"closed","provider":"Anthropic","task":"pelican_bicycle","sample":19,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle.","answer_chars":3879,"reasoning_chars":0,"latency_s":43.85,"svg":"svg/claude-opus-5__pelican_bicycle__019.svg","png":"png/claude-opus-5__pelican_bicycle__019.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/claude-opus-5__pelican_bicycle__019.svg","localSvg":"/media/benchmark/openenv-2026-07-29/claude-opus-5__pelican_bicycle__019.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-claude-opus-5-20.png","latency":43.85,"tags":["benchmark"],"recordId":"hf-openenv-claude-opus-5-sample-20-2026-07-29","recordPath":"/specimens/hf-openenv-claude-opus-5-sample-20-2026-07-29/","sha256":{"svg":"d62b624aaa7e67ed5c90e6eb1f7d67aab386aac864e9ee34349ebec2ca0d6eb7","png":"0101eca8f0a5e198046406098c3f85239ff899d23f1bdd92a14e4e5c08edc934"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__000","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":0,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on a grassy path under a blue sky.","answer_chars":6231,"reasoning_chars":0,"latency_s":35.89,"svg":"svg/gpt-5.6-sol__pelican_bicycle__000.svg","png":"png/gpt-5.6-sol__pelican_bicycle__000.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__000.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__000.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-01.png","latency":35.89,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-01-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-01-2026-07-29/","sha256":{"svg":"98a69224902ce44d012649ed265bbb7bbb0cfc8e7294880d68c41ff7f91b30b0","png":"ee74abe836ae41e3e6eb2a9061d1dae661a552be3d5529d063576efc4bd555dc"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__001","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":1,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a blue bicycle on a grassy path under a sunny sky with birds flying.","answer_chars":7743,"reasoning_chars":0,"latency_s":54.6,"svg":"svg/gpt-5.6-sol__pelican_bicycle__001.svg","png":"png/gpt-5.6-sol__pelican_bicycle__001.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__001.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__001.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-02.png","latency":54.6,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-02-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-02-2026-07-29/","sha256":{"svg":"05de1f2a0b89c461725b2325b2855400c36a33dbd7143b083563d0c11303946e","png":"eeb94c4182f93e1a4f0f6501b094bbd2b02567b80b978485f3f71fe75f210f4f"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__002","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":2,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on a grassy field under a sunny sky with clouds.","answer_chars":7029,"reasoning_chars":0,"latency_s":38.06,"svg":"svg/gpt-5.6-sol__pelican_bicycle__002.svg","png":"png/gpt-5.6-sol__pelican_bicycle__002.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__002.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__002.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-03.png","latency":38.06,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-03-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-03-2026-07-29/","sha256":{"svg":"853fb459b4cf0c3a2a610d0fc9ea9ea6bb846f46f8e9c9dc50dcec7981a9e80c","png":"23da58df027bc18360ec86609cf1e5c03fabea0029f4341da59c39b6593549ba"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__003","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":3,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon duck is riding a red bicycle on grass under a blue sky with clouds and a sun.","answer_chars":7374,"reasoning_chars":0,"latency_s":40.36,"svg":"svg/gpt-5.6-sol__pelican_bicycle__003.svg","png":"png/gpt-5.6-sol__pelican_bicycle__003.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__003.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__003.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-04.png","latency":40.36,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-04-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-04-2026-07-29/","sha256":{"svg":"5445f02fc4c7c72c73bcd0378e5e640bd32bef15c39094f8cc9091691dc57e86","png":"2a40fff97fffa1c8b133b5a4b1b2ecb6ef739b45c9cfa7ac55a649d584b30898"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__004","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":4,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with an orange beak and legs is riding a blue bicycle.","answer_chars":7858,"reasoning_chars":0,"latency_s":41.9,"svg":"svg/gpt-5.6-sol__pelican_bicycle__004.svg","png":"png/gpt-5.6-sol__pelican_bicycle__004.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__004.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__004.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-05.png","latency":41.9,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-05-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-05-2026-07-29/","sha256":{"svg":"81c70a51d4959e6473d46193f2bcae531705fff0f3ca457a29365e5bc83828a3","png":"816f879e83bc77bcf20c6fab14950916295b03e21248d7f71b51b8123ad9f4f5"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__005","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":5,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a blue bicycle on grass under a blue sky with clouds.","answer_chars":7635,"reasoning_chars":0,"latency_s":46.92,"svg":"svg/gpt-5.6-sol__pelican_bicycle__005.svg","png":"png/gpt-5.6-sol__pelican_bicycle__005.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__005.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__005.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-06.png","latency":46.92,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-06-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-06-2026-07-29/","sha256":{"svg":"6793417c571f8fed09c3574bb68c670a5b06ca6a1ca42659983057461625b2e8","png":"fe131e35282e7cdb169e3b7980824cf430dba5d4f36bfac602608af1dd8c1f03"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__006","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":6,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with an orange beak is riding a red bicycle on a grassy path.","answer_chars":5720,"reasoning_chars":0,"latency_s":31.43,"svg":"svg/gpt-5.6-sol__pelican_bicycle__006.svg","png":"png/gpt-5.6-sol__pelican_bicycle__006.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__006.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__006.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-07.png","latency":31.43,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-07-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-07-2026-07-29/","sha256":{"svg":"35d1a58cc557bfa011cefd7b04cd95ba753ed8b7efdc6b03e4a9ef5491dbc55d","png":"18ad1b6157165c1a0e78cb2a2c2a31d70721e1203de2f41e3f40d19ca9634f52"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__007","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":7,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on grass with a blue sky background.","answer_chars":5679,"reasoning_chars":0,"latency_s":33.97,"svg":"svg/gpt-5.6-sol__pelican_bicycle__007.svg","png":"png/gpt-5.6-sol__pelican_bicycle__007.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__007.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__007.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-08.png","latency":33.97,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-08-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-08-2026-07-29/","sha256":{"svg":"8264ba9de175a87cd54fc16db886b6aad7a44491bf8939e48cc0e044258a301d","png":"5eb47bb6919d4b7387eb77e018e77dbf800005037177fe7af539ad6a1cdd07a4"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__008","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":8,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle.","answer_chars":6641,"reasoning_chars":0,"latency_s":38.62,"svg":"svg/gpt-5.6-sol__pelican_bicycle__008.svg","png":"png/gpt-5.6-sol__pelican_bicycle__008.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__008.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__008.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-09.png","latency":38.62,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-09-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-09-2026-07-29/","sha256":{"svg":"979cb8b44c9debcb8cabf0b1b60ddb6a8ce224d4178f6aba327d45076df491a6","png":"291466c13ce1016741b065a60f530255f10f0227ee0d9fd93a42eeb02f10937e"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__009","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":9,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on a road with green hills, a yellow sun, and two birds flying in the sky.","answer_chars":7052,"reasoning_chars":0,"latency_s":37.22,"svg":"svg/gpt-5.6-sol__pelican_bicycle__009.svg","png":"png/gpt-5.6-sol__pelican_bicycle__009.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__009.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__009.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-10.png","latency":37.22,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-10-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-10-2026-07-29/","sha256":{"svg":"221b4550554a2295cdce5d4221dd4473dad215c3991505c34bdaebb46a98f0c8","png":"e050173b3e27ae7c9bae7716b9133099afa68888a75f41fa27e994549d03a684"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__010","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":10,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle with a yellow sun in the background.","answer_chars":5998,"reasoning_chars":0,"latency_s":32.35,"svg":"svg/gpt-5.6-sol__pelican_bicycle__010.svg","png":"png/gpt-5.6-sol__pelican_bicycle__010.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__010.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__010.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-11.png","latency":32.35,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-11-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-11-2026-07-29/","sha256":{"svg":"c62f4def3791e978f3852cef38fbac8cae5cef27c8fa54ed1af86246401d2e03","png":"5bc7bc584b8acaee1a55fa924699d7e446e38258fdb08eec0b3014ef86d59276"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__011","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":11,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with an orange beak is riding a red bicycle on a green surface.","answer_chars":5651,"reasoning_chars":0,"latency_s":28.37,"svg":"svg/gpt-5.6-sol__pelican_bicycle__011.svg","png":"png/gpt-5.6-sol__pelican_bicycle__011.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__011.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__011.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-12.png","latency":28.37,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-12-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-12-2026-07-29/","sha256":{"svg":"38651a7f39e1f1a7907a29427bc7baf2cb8f83ab08bd7755f4e7ee03660ccceb","png":"a9d84ac2c35c4eb3c54cb3e21b3c7923aeaf7787ad2a1f0b010348af87aa1e94"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__012","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":12,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon goose with an orange beak is riding a red bicycle on a grassy hill under a blue sky.","answer_chars":5986,"reasoning_chars":0,"latency_s":35.3,"svg":"svg/gpt-5.6-sol__pelican_bicycle__012.svg","png":"png/gpt-5.6-sol__pelican_bicycle__012.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__012.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__012.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-13.png","latency":35.3,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-13-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-13-2026-07-29/","sha256":{"svg":"7a321f18c1364000a338e7dc82fa58b849a388302a8ca93046bc32104b1f9c41","png":"a33a65f5bf591cc8251279dc90193146d06ddda6f7397e5d6ab987e39366fcd7"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__013","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":13,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with grass below.","answer_chars":7278,"reasoning_chars":0,"latency_s":49.22,"svg":"svg/gpt-5.6-sol__pelican_bicycle__013.svg","png":"png/gpt-5.6-sol__pelican_bicycle__013.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__013.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__013.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-14.png","latency":49.22,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-14-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-14-2026-07-29/","sha256":{"svg":"c6b077915a2ae4c95529dd314d7a9af59db85cbbaebd372c8afc15522b88c4df","png":"9bc55228f0748444c091960cdb000ebc49a14800a21668a70e02a7265eb94f5f"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__014","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":14,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with an orange beak is riding a red bicycle on a grassy path.","answer_chars":6063,"reasoning_chars":0,"latency_s":32.81,"svg":"svg/gpt-5.6-sol__pelican_bicycle__014.svg","png":"png/gpt-5.6-sol__pelican_bicycle__014.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__014.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__014.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-15.png","latency":32.81,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-15-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-15-2026-07-29/","sha256":{"svg":"7915159fff02523885ed62587f683933f62569a262c2ffc3f7978a8ccf30eee4","png":"9363f2ae5d2d10196570cdba3d57e6d65878b8d96dfb5de5f7859d82be180d86"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__015","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":15,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on grass under a sunny sky with a bird flying above.","answer_chars":7120,"reasoning_chars":0,"latency_s":43.87,"svg":"svg/gpt-5.6-sol__pelican_bicycle__015.svg","png":"png/gpt-5.6-sol__pelican_bicycle__015.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__015.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__015.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-16.png","latency":43.87,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-16-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-16-2026-07-29/","sha256":{"svg":"af7f1401b09d37b8e60b70586e9e3bdd27b9e0f940b5e889217a713304f72d4b","png":"90180ea4b52482fccdd77064d0eebfded06d1dd24c644e19a28feefa01122fc0"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__016","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":16,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on a grassy hill under a sunny sky.","answer_chars":5790,"reasoning_chars":0,"latency_s":34.22,"svg":"svg/gpt-5.6-sol__pelican_bicycle__016.svg","png":"png/gpt-5.6-sol__pelican_bicycle__016.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__016.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__016.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-17.png","latency":34.22,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-17-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-17-2026-07-29/","sha256":{"svg":"4c37a69359e41952c2a2c4c6f43ce37f95c101f4c3edf6f4d28f1a1be0618eec","png":"9609832338b19d45dd13a8669fd0e97966dafeaa9d5c06af535ee87aef9df4b1"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__017","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":17,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on a grassy hill under a blue sky.","answer_chars":5315,"reasoning_chars":0,"latency_s":33.85,"svg":"svg/gpt-5.6-sol__pelican_bicycle__017.svg","png":"png/gpt-5.6-sol__pelican_bicycle__017.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__017.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__017.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-18.png","latency":33.85,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-18-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-18-2026-07-29/","sha256":{"svg":"89c6c0ea599f73a1785be397b1ce6985964bcc681b7937d754cc515c1ff3ce3f","png":"a945217cae78ff2fca49f450909de9d7b7db8ffb432bf295836328953f5f782c"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__018","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":18,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with clouds.","answer_chars":8433,"reasoning_chars":0,"latency_s":42.15,"svg":"svg/gpt-5.6-sol__pelican_bicycle__018.svg","png":"png/gpt-5.6-sol__pelican_bicycle__018.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__018.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__018.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-19.png","latency":42.15,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-19-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-19-2026-07-29/","sha256":{"svg":"26a882f2def4fdd30c6756d135edc3933844ea6b298d015dc8265f64d80c5abc","png":"83786a041fc23cf6a324fcb0c343b2470cb8ef0b58b747a3fb3ea0850d159e46"},"mediaStatus":"local"},{"id":"gpt-5.6-sol__pelican_bicycle__019","model":"gpt-5.6-sol","access":"closed","provider":"OpenAI","task":"pelican_bicycle","sample":19,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on grass under a blue sky with clouds.","answer_chars":9384,"reasoning_chars":0,"latency_s":84.64,"svg":"svg/gpt-5.6-sol__pelican_bicycle__019.svg","png":"png/gpt-5.6-sol__pelican_bicycle__019.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/gpt-5.6-sol__pelican_bicycle__019.svg","localSvg":"/media/benchmark/openenv-2026-07-29/gpt-5.6-sol__pelican_bicycle__019.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-gpt-5-6-sol-20.png","latency":84.64,"tags":["benchmark"],"recordId":"hf-openenv-gpt-5-6-sol-sample-20-2026-07-29","recordPath":"/specimens/hf-openenv-gpt-5-6-sol-sample-20-2026-07-29/","sha256":{"svg":"3db2929a40461f3fe5ad2e07883dc1ddd7322326859ec817eda09216347769f8","png":"f7238b6294c09cfe0b1d11707c8f17b2163935cd4cd044c446532086f2daf87f"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__000","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":0,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a sunny sky with clouds.","answer_chars":6550,"reasoning_chars":24803,"latency_s":368.02,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__000.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__000.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__000.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__000.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-01.png","latency":368.02,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-01-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-01-2026-07-29/","sha256":{"svg":"c39eccbed798c68f35d5953c2326ad67d96ba8cbed959b298962c732b74f60f9","png":"8347d0281a9954edee7ce056ecba1f49e3aae6c9dcb444c0a9d2c142b6b688f2"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__001","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":1,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with clouds.","answer_chars":5352,"reasoning_chars":24228,"latency_s":354.78,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__001.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__001.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__001.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__001.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-02.png","latency":354.78,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-02-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-02-2026-07-29/","sha256":{"svg":"1e0b8e04a49bb950371132f836a428b37dbe752ba648bc0e145a95bb0d2015a8","png":"1c1d3e00b77e5957defa076098f523182b7df7d5c8f71256f3f2c701da910875"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__002","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":2,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with a cloud and sun visible.","answer_chars":6233,"reasoning_chars":40544,"latency_s":473.92,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__002.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__002.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__002.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__002.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-03.png","latency":473.92,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-03-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-03-2026-07-29/","sha256":{"svg":"7dbee7d660839ff4ee1eea25d72be79f4d2fe7a7ddb629f723cd364d8269f713","png":"f2333c8ed6a6ffeb00f80a1b3a131b99d5d4f906a2b90ee2bcb8c7db03503d43"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__003","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":3,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with clouds.","answer_chars":6265,"reasoning_chars":37570,"latency_s":444.65,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__003.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__003.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__003.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__003.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-04.png","latency":444.65,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-04-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-04-2026-07-29/","sha256":{"svg":"68d828e5e0300724f826901f201f754555e85383922a1fd66b8e2781559b1f33","png":"d5ea63d23ab024c3071aaaf71caa0b88176d05cae67025ad0ad849533ce126f3"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__004","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":4,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle on grass under a blue sky with a cloud and a yellow sun.","answer_chars":5424,"reasoning_chars":16117,"latency_s":178.86,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__004.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__004.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__004.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__004.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-05.png","latency":178.86,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-05-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-05-2026-07-29/","sha256":{"svg":"b7298aa5f7735a0ed7770196fa34a1f9df3c33b48848734934007d734fbfa431","png":"30f37df811b4961a14b60243abf7629bae4f9c84738efb373c73ce5d20294826"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__005","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":5,"reward":0.0,"structure_score":0.0,"semantic_score":0.0,"gate_passed":false,"violations":["truncated_svg"],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"","answer_chars":3863,"reasoning_chars":14659,"latency_s":214.51,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__005.svg","png":null,"config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__005.svg","localSvg":null,"localPng":null,"latency":214.51,"tags":["benchmark"],"mediaStatus":"unrenderable"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__006","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":6,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with clouds.","answer_chars":6692,"reasoning_chars":21369,"latency_s":258.13,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__006.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__006.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__006.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__006.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-07.png","latency":258.13,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-07-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-07-2026-07-29/","sha256":{"svg":"a6dadb5f0389932adcd06d2299c2096451fe6ced1424315d2e119de3ab59eabf","png":"72c95e1e4620c66e1b92f3fca782f89503c6fe54037988bf772df2a2c74015b2"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__008","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":8,"reward":0.8013888888888889,"structure_score":1.0,"semantic_score":0.6944444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A stork is riding a red bicycle under a sunny sky with clouds.","answer_chars":5824,"reasoning_chars":33320,"latency_s":382.87,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__008.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__008.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__008.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__008.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-09.png","latency":382.87,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-09-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-09-2026-07-29/","sha256":{"svg":"81cc89e9e0b8e7399e3c28d45e3140e63b2f70241e08fcbe85783dca65f7fa63","png":"d21082f737d7f9f2124d7d5f9b8f3b8ba48f65d0c9cad20e99213aaf333ad1f3"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__009","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":9,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican wearing a red helmet rides a red bicycle under a sunny sky with clouds.","answer_chars":6276,"reasoning_chars":28193,"latency_s":324.34,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__009.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__009.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__009.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__009.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-10.png","latency":324.34,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-10-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-10-2026-07-29/","sha256":{"svg":"5557ac66edd7e0edd0b1fd34d5982ce5b49e1f61cb868a1da8d2f158d4ff9cb9","png":"55acb89716e8f22d977acf78cd0d28fa5e5b8a8fa48e07b587ad3a250975a97f"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__010","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":10,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork wearing a red scarf is riding a red bicycle under a sunny sky with clouds and birds.","answer_chars":7708,"reasoning_chars":36312,"latency_s":378.0,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__010.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__010.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__010.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__010.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-11.png","latency":378.0,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-11-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-11-2026-07-29/","sha256":{"svg":"8ac37d3509bc5f1c988bc1c6fa6a57211a47896a73c26cccba81f424f647ac73","png":"42c08cd5b77c6f08fec87d22061c8b862db081109b299716e6af0e9b711fc010"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__011","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":11,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a sunny sky with clouds.","answer_chars":7295,"reasoning_chars":26278,"latency_s":331.39,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__011.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__011.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__011.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__011.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-12.png","latency":331.39,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-12-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-12-2026-07-29/","sha256":{"svg":"73b1e5d92327d761a969cb7823205c33183556fd16607d00e32652f7edcd5f33","png":"3df8f4d0fb8c97f3ad12461817aa84b86be616ca3c69f00c2a3a4126b298caa8"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__012","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":12,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle under a sunny sky with clouds.","answer_chars":7217,"reasoning_chars":25200,"latency_s":279.25,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__012.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__012.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__012.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__012.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-13.png","latency":279.25,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-13-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-13-2026-07-29/","sha256":{"svg":"08dac16368ced5a7252f443112775e08289f766ae110040166b369b4c0d9b262","png":"2b0beb9e4a9060fcd32d33f2912fa84e8179be3dc27725b48f0f32ff9d8b7135"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__013","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":13,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with clouds.","answer_chars":6025,"reasoning_chars":40349,"latency_s":542.65,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__013.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__013.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__013.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__013.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-14.png","latency":542.65,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-14-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-14-2026-07-29/","sha256":{"svg":"9fd2e2a96d83a753b5c8c9142b06074e51854c4795f95f172b43c2c6d072e74c","png":"62c379ae17953ea0e7dea9024ee173dfaf39a5e7b64ce0320cf05338b600126b"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__014","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":14,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a bicycle under a sunny sky with clouds.","answer_chars":6362,"reasoning_chars":29418,"latency_s":368.53,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__014.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__014.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__014.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__014.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-15.png","latency":368.53,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-15-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-15-2026-07-29/","sha256":{"svg":"11d19fcc274d92d28f2673c7da85c2555978e47b8278fcdc7c3e80a1c9c5b34a","png":"96e353d071af774b466c5d682f12dce61938855664be7469894b08549621decf"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__015","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":15,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with clouds.","answer_chars":6357,"reasoning_chars":38879,"latency_s":394.98,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__015.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__015.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__015.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__015.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-16.png","latency":394.98,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-16-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-16-2026-07-29/","sha256":{"svg":"5822850ca2bae90be6dee30b88ea7d355cf12f660393fcfca2bcc11038bc722d","png":"4a8c6c27251fc945eb0aac84656d98752c7bf6dd6897a9b2196e164e215a140b"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__016","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":16,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a green bicycle under a sunny sky with a cloud.","answer_chars":5979,"reasoning_chars":39218,"latency_s":494.77,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__016.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__016.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__016.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__016.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-17.png","latency":494.77,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-17-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-17-2026-07-29/","sha256":{"svg":"1c3cb5e3ee3ee47ab380159d24763cdfb9acd5ffbcd5c8d4e92840f999036f8e","png":"188c985bc1db226ae64519d838e1ae42b2c4a03d25e61e637058feec473cc03f"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__017","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":17,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle under a sunny sky with clouds.","answer_chars":5515,"reasoning_chars":27738,"latency_s":357.67,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__017.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__017.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__017.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__017.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-18.png","latency":357.67,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-18-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-18-2026-07-29/","sha256":{"svg":"4f6da48456cb28e7a6357d9fd45ba6db1b54a039adff8a9b1a22eb1d237b6de9","png":"5178196ad4235167c0549a51ba82e019a2e8b831b7fe575cf2cfc09b1e5e88bb"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__018","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":18,"reward":0.8013888888888889,"structure_score":1.0,"semantic_score":0.6944444444444444,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a red bicycle with a baby carriage attached, under a sunny sky with a cloud and sun visible.","answer_chars":5116,"reasoning_chars":30847,"latency_s":449.24,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__018.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__018.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__018.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__018.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-19.png","latency":449.24,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-19-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-19-2026-07-29/","sha256":{"svg":"0efd5616142e48b52c2b31a3dad85c946c97745657821b22c9fbd7919be25450","png":"357ef5df49669a4a2450a18909ca740c439243e4a0825a5f1016ec28576ea1bc"},"mediaStatus":"local"},{"id":"moonshotai__Kimi-K3__pelican_bicycle__019","model":"moonshotai/Kimi-K3","access":"open","provider":"hf-inference-providers","task":"pelican_bicycle","sample":19,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"violations":[],"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican wearing a red cap rides a red bicycle under a sunny sky with clouds.","answer_chars":6983,"reasoning_chars":32236,"latency_s":476.76,"svg":"svg/moonshotai__Kimi-K3__pelican_bicycle__019.svg","png":"png/moonshotai__Kimi-K3__pelican_bicycle__019.png","config":"default","missingSourceFields":[],"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/moonshotai__Kimi-K3__pelican_bicycle__019.svg","localSvg":"/media/benchmark/openenv-2026-07-29/moonshotai__Kimi-K3__pelican_bicycle__019.svg","localPng":"/media/collected/2026-10-01-source-backfill/hf-moonshotai-kimi-k3-20.png","latency":476.76,"tags":["benchmark"],"recordId":"hf-openenv-moonshotai-kimi-k3-sample-20-2026-07-29","recordPath":"/specimens/hf-openenv-moonshotai-kimi-k3-sample-20-2026-07-29/","sha256":{"svg":"b331ff909063bdc2497793fbdd7a3441ef47c5f3654193448e7a35420d3b75e0","png":"4c7c885e723001cfa31ec573c944fa7c17fe2d3ef69880a3aa511e0b1588de11"},"mediaStatus":"local"},{"id":"coverage__pelican_bicycle","task":"pelican_bicycle","subject":"pelican","vehicle":"bicycle","expected_wheels":2,"held_out":false,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon pelican is riding a red bicycle with clouds in the background.","svg":"svg/coverage__pelican_bicycle.svg","png":"png/coverage__pelican_bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__pelican_bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__pelican_bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__pelican_bicycle.png","latency":null,"tags":["benchmark"],"sha256":{"svg":"8987817661929e2f6dc4d80ae86bd1290914ca36bcb3738a6311715b54f88725","png":"8f51e4e83bb503369a72980e98bbe317dcbec74a610fda47678db4145af50321"},"mediaStatus":"local"},{"id":"coverage__pelican_unicycle","task":"pelican_unicycle","subject":"pelican","vehicle":"unicycle","expected_wheels":1,"held_out":true,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bird with a yellow beak and legs is riding a unicycle.","svg":"svg/coverage__pelican_unicycle.svg","png":"png/coverage__pelican_unicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__pelican_unicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__pelican_unicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__pelican_unicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"ca454ff462ef47b6aa488426e87cf871f07f6d590532cdc95b446b94590d767c","png":"758e4a582bade57311a95230d76591d23a4257c0427498cf17c58d3237c923a0"},"mediaStatus":"local"},{"id":"coverage__pelican_tandem-bicycle","task":"pelican_tandem-bicycle","subject":"pelican","vehicle":"tandem bicycle","expected_wheels":2,"held_out":true,"reward":0.65625,"structure_score":0.7142857142857143,"semantic_score":0.625,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"Two white birds with orange beaks are riding a red tandem bicycle under a sunny blue sky with clouds and a few birds flying.","svg":"svg/coverage__pelican_tandem-bicycle.svg","png":"png/coverage__pelican_tandem-bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__pelican_tandem-bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__pelican_tandem-bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__pelican_tandem-bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"83f2c6985370030efa2d184074ce5a542709b1e26de58527937f0f57591a50ff","png":"316c915f913e904adb8230cc2e7e3b80feedbfde8717c82c77b3819567a72310"},"mediaStatus":"local"},{"id":"coverage__pelican_scooter","task":"pelican_scooter","subject":"pelican","vehicle":"scooter","expected_wheels":2,"held_out":true,"reward":0.715625,"structure_score":1.0,"semantic_score":0.5625,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is riding a scooter on a road with grass, clouds, and a sun in the background.","svg":"svg/coverage__pelican_scooter.svg","png":"png/coverage__pelican_scooter.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__pelican_scooter.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__pelican_scooter.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__pelican_scooter.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"b65b69f3874df888787088dabbbf889ea27ba7e3229dd3fda048358dd3869253","png":"726da6b1ca55ff39f8d10db57ffb5ccb3a07cc02d3fe098cb0bbc2e32d981c56"},"mediaStatus":"local"},{"id":"coverage__pelican_skateboard","task":"pelican_skateboard","subject":"pelican","vehicle":"skateboard","expected_wheels":2,"held_out":true,"reward":0.625,"structure_score":0.8571428571428571,"semantic_score":0.5,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon stork is skateboarding on a road under a sunny sky with clouds.","svg":"svg/coverage__pelican_skateboard.svg","png":"png/coverage__pelican_skateboard.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__pelican_skateboard.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__pelican_skateboard.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__pelican_skateboard.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"cfac31e6f2429b5b074f532c9c1c49d63e4e3f89b73242be6510bedb98691dc4","png":"16a7cb307b4f29cebdb0d6160c8670dacce175baf74a4670ce9b8c14d11528ca"},"mediaStatus":"local"},{"id":"coverage__flamingo_bicycle","task":"flamingo_bicycle","subject":"flamingo","vehicle":"bicycle","expected_wheels":2,"held_out":true,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink flamingo is riding a red bicycle under a blue sky with clouds and a sun.","svg":"svg/coverage__flamingo_bicycle.svg","png":"png/coverage__flamingo_bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__flamingo_bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"08cd437dc5b230528de3ddeec8e77bc6e1953756c56e4540db949aab71f31524","png":"d2437ae04f25d20c8c0a42a28eb969883e720bda0ab580b1fdae1f24df87cad9"},"mediaStatus":"local"},{"id":"coverage__flamingo_unicycle","task":"flamingo_unicycle","subject":"flamingo","vehicle":"unicycle","expected_wheels":1,"held_out":true,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink flamingo is riding a unicycle on grass under a blue sky with clouds and a sun.","svg":"svg/coverage__flamingo_unicycle.svg","png":"png/coverage__flamingo_unicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__flamingo_unicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_unicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_unicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"36e460c5a7b5a1c1c5f9a676ebc27b0bb9370746dbdcb003f18a931eaebea14b","png":"b362991e85046f40ec961a272b48280411f7b7d77aa700da2ba98c76bf550887"},"mediaStatus":"local"},{"id":"coverage__flamingo_tandem-bicycle","task":"flamingo_tandem-bicycle","subject":"flamingo","vehicle":"tandem bicycle","expected_wheels":2,"held_out":true,"reward":0.7375,"structure_score":0.7142857142857143,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"Two pink flamingos are riding a tandem bicycle under a sunny sky with clouds and grass below.","svg":"svg/coverage__flamingo_tandem-bicycle.svg","png":"png/coverage__flamingo_tandem-bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__flamingo_tandem-bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_tandem-bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_tandem-bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"d24c40a84488f4de907d8263ff382fd4911ee10d163f118801bed84602c76174","png":"fedbb326144891b8930af83bc178aacf39cc9fd5156369cdbee382063ef0f25b"},"mediaStatus":"local"},{"id":"coverage__flamingo_scooter","task":"flamingo_scooter","subject":"flamingo","vehicle":"scooter","expected_wheels":2,"held_out":true,"reward":0.91875,"structure_score":1.0,"semantic_score":0.875,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink flamingo is riding a scooter on grass under a blue sky with clouds and a sun.","svg":"svg/coverage__flamingo_scooter.svg","png":"png/coverage__flamingo_scooter.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__flamingo_scooter.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_scooter.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_scooter.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"57313b3cd795ded0a609f78f714b573481abf4d7c51044fb0e177920321d36c2","png":"8dbcee78f4f4d52582657dce50c8fb8fd1943a7c4b3517fc7623d9e3e64ef76f"},"mediaStatus":"local"},{"id":"coverage__flamingo_skateboard","task":"flamingo_skateboard","subject":"flamingo","vehicle":"skateboard","expected_wheels":2,"held_out":true,"reward":0.9,"structure_score":0.7142857142857143,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink flamingo is riding on a skateboard under a blue sky with clouds and a yellow sun.","svg":"svg/coverage__flamingo_skateboard.svg","png":"png/coverage__flamingo_skateboard.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__flamingo_skateboard.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_skateboard.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__flamingo_skateboard.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"0c6a9bf6c9f91b40081230b91c351783e5bfe9c32b0f58dcb2edcf1b87e3c718","png":"858c152b856ff0aa3532d8cf9024cc25f7315f37552b5d8cbdaae5eee1b611f7"},"mediaStatus":"local"},{"id":"coverage__capybara_bicycle","task":"capybara_bicycle","subject":"capybara","vehicle":"bicycle","expected_wheels":2,"held_out":true,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bear is riding a red bicycle on a green ground with a blue background.","svg":"svg/coverage__capybara_bicycle.svg","png":"png/coverage__capybara_bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__capybara_bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__capybara_bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__capybara_bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"94a78d71f581d39615ba1212f2425de26f9c6657588e4c2a84a7aea7fb1d86e1","png":"0c6c150e303fdae0e831f02ccb773b3dd945523b4a2cc521c8bbd12aeffb2264"},"mediaStatus":"local"},{"id":"coverage__capybara_unicycle","task":"capybara_unicycle","subject":"capybara","vehicle":"unicycle","expected_wheels":1,"held_out":true,"reward":0.715625,"structure_score":1.0,"semantic_score":0.5625,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bear is riding a unicycle on a green line with motion lines indicating movement.","svg":"svg/coverage__capybara_unicycle.svg","png":"png/coverage__capybara_unicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__capybara_unicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__capybara_unicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__capybara_unicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"559979cdf0344613304a87fe96842ed6236586fdcf3bf814d3d6449ae98cc23e","png":"d085409a73396a8029be6a42c0ace1ece5eafa12974e636134e7df6f4c95ac12"},"mediaStatus":"local"},{"id":"coverage__capybara_tandem-bicycle","task":"capybara_tandem-bicycle","subject":"capybara","vehicle":"tandem bicycle","expected_wheels":2,"held_out":true,"reward":0.7375,"structure_score":0.7142857142857143,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"Two cartoon capybaras are riding a tandem bicycle on a sunny day with clouds and bushes visible.","svg":"svg/coverage__capybara_tandem-bicycle.svg","png":"png/coverage__capybara_tandem-bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__capybara_tandem-bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__capybara_tandem-bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__capybara_tandem-bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"29c0c8e7614278de4fafc1f2df63fca5120ad27bf989e785fe2b22068a525a27","png":"c4e93778b6bedd0367a367a532da99594129d2c3bd5091f3cb488801a21ffddd"},"mediaStatus":"local"},{"id":"coverage__capybara_scooter","task":"capybara_scooter","subject":"capybara","vehicle":"scooter","expected_wheels":2,"held_out":true,"reward":0.553125,"structure_score":1.0,"semantic_score":0.3125,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bear is riding a red bicycle on a road under a blue sky with clouds and a yellow sun.","svg":"svg/coverage__capybara_scooter.svg","png":"png/coverage__capybara_scooter.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__capybara_scooter.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__capybara_scooter.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__capybara_scooter.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"3c8adc1f1478147c39e87992030ca9f83eafde5fba8ca6dd4df341dc984bc17f","png":"964ae5b3bda78b39e981f4d413a967e5f58945613f4e7014d6840e89b0c6ed63"},"mediaStatus":"local"},{"id":"coverage__capybara_skateboard","task":"capybara_skateboard","subject":"capybara","vehicle":"skateboard","expected_wheels":2,"held_out":true,"reward":0.6375000000000001,"structure_score":0.42857142857142855,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon bear is standing on a skateboard under a blue sky with clouds and a yellow sun.","svg":"svg/coverage__capybara_skateboard.svg","png":"png/coverage__capybara_skateboard.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__capybara_skateboard.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__capybara_skateboard.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__capybara_skateboard.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"4cee33fc4e6b09ceb91be7e961acb794e20542dc4d69d6c5cec602a805dd5863","png":"c7c10a0f7f42db3dc2bcdee0bc4326efff1442562d328b6e3b43ba1436f9e881"},"mediaStatus":"local"},{"id":"coverage__axolotl_bicycle","task":"axolotl_bicycle","subject":"axolotl","vehicle":"bicycle","expected_wheels":2,"held_out":true,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink, cartoonish creature with multiple limbs is riding a red bicycle.","svg":"svg/coverage__axolotl_bicycle.svg","png":"png/coverage__axolotl_bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__axolotl_bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"0666b1eb37b223361b40a7e84c77c22b21a56600e7cbf38acbcb781882fc8294","png":"b72344907608c1e4050e9df35d4f86256ef6dbcf6f0edff634e10d7e49ded6a4"},"mediaStatus":"local"},{"id":"coverage__axolotl_unicycle","task":"axolotl_unicycle","subject":"axolotl","vehicle":"unicycle","expected_wheels":1,"held_out":true,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink cartoon character with red spikes is riding a unicycle on grass under a blue sky with clouds and stars.","svg":"svg/coverage__axolotl_unicycle.svg","png":"png/coverage__axolotl_unicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__axolotl_unicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_unicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_unicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"d67afd9bd5c557da27023981428fd18e7462464d9bada4e3de2fc31faf84de87","png":"3b84e4602e4f639f884a59720171a702f9fc2c116e992fbdf6423752545617d6"},"mediaStatus":"local"},{"id":"coverage__axolotl_tandem-bicycle","task":"axolotl_tandem-bicycle","subject":"axolotl","vehicle":"tandem bicycle","expected_wheels":2,"held_out":true,"reward":0.7375,"structure_score":0.7142857142857143,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"Two cartoonish creatures with pink and purple bodies are riding a tandem bicycle under a sunny blue sky with clouds.","svg":"svg/coverage__axolotl_tandem-bicycle.svg","png":"png/coverage__axolotl_tandem-bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__axolotl_tandem-bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_tandem-bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_tandem-bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"169922d7e743e07982dc4df8484459428d73ddcde810235ce65bb1ff4fa0f789","png":"1ce626b11f2b1ef3cfd1b97980b96e91cd3b238adf7fc836573fa650fff940fd"},"mediaStatus":"local"},{"id":"coverage__axolotl_scooter","task":"axolotl_scooter","subject":"axolotl","vehicle":"scooter","expected_wheels":2,"held_out":true,"reward":0.796875,"structure_score":1.0,"semantic_score":0.6875,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink cartoon character with antennae is riding a blue scooter under a sunny sky with clouds and grass below.","svg":"svg/coverage__axolotl_scooter.svg","png":"png/coverage__axolotl_scooter.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__axolotl_scooter.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_scooter.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_scooter.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"7ea48a891e5d9005b9c4941393cba42ec720a170e617bd28f8d9415d58ccc7c8","png":"adfeae94266a1dfe035754c01ae528f4323f2d65417690b8908fa681a7627535"},"mediaStatus":"local"},{"id":"coverage__axolotl_skateboard","task":"axolotl_skateboard","subject":"axolotl","vehicle":"skateboard","expected_wheels":2,"held_out":true,"reward":0.7875000000000001,"structure_score":0.8571428571428571,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink cartoon character with antennae is sitting on a skateboard under a sunny sky with clouds and trees.","svg":"svg/coverage__axolotl_skateboard.svg","png":"png/coverage__axolotl_skateboard.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__axolotl_skateboard.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_skateboard.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__axolotl_skateboard.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"6303508d533596b0fc0d9a591451235f165839d9f163e66a51428976196e27d7","png":"9c697645448964eb7d551fb31e6763113e26de60910ddb8174e74a0228fae0ef"},"mediaStatus":"local"},{"id":"coverage__octopus_bicycle","task":"octopus_bicycle","subject":"octopus","vehicle":"bicycle","expected_wheels":2,"held_out":true,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A purple octopus is riding a red bicycle with bubbles floating around.","svg":"svg/coverage__octopus_bicycle.svg","png":"png/coverage__octopus_bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__octopus_bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__octopus_bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__octopus_bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"089171248d83813a6b036d5e6bdb7b09c0447d2607fdb1f4036dacf597915785","png":"b8400069d1c2920886692c06f41db328e23993ba470c044ce16a573667d4d0b8"},"mediaStatus":"local"},{"id":"coverage__octopus_unicycle","task":"octopus_unicycle","subject":"octopus","vehicle":"unicycle","expected_wheels":1,"held_out":true,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A purple octopus is riding a unicycle against a dark background with small yellow dots.","svg":"svg/coverage__octopus_unicycle.svg","png":"png/coverage__octopus_unicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__octopus_unicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__octopus_unicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__octopus_unicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"fd26ab9d865ba138fe7717c5a8773207f458bda817007b9d1c9cc679b1f654a1","png":"6ea915b8d79cc62a274d1db57cb414823adb2c8b67deb7644c39ba72e54625ef"},"mediaStatus":"local"},{"id":"coverage__octopus_tandem-bicycle","task":"octopus_tandem-bicycle","subject":"octopus","vehicle":"tandem bicycle","expected_wheels":2,"held_out":true,"reward":0.8375,"structure_score":1.0,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink octopus is riding a red bicycle on a road with a blue sky and clouds in the background.","svg":"svg/coverage__octopus_tandem-bicycle.svg","png":"png/coverage__octopus_tandem-bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__octopus_tandem-bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__octopus_tandem-bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__octopus_tandem-bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"9a412ef1e89ee793c3eabc1d1cd4fc5014c374a160cd58715ae3b2456f28ecb6","png":"4d3460ef2d98f56aa25143f74d951752b78e41188c2e4a28a66930fa73b3989d"},"mediaStatus":"local"},{"id":"coverage__octopus_scooter","task":"octopus_scooter","subject":"octopus","vehicle":"scooter","expected_wheels":2,"held_out":true,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A pink octopus is riding a blue scooter with two wheels.","svg":"svg/coverage__octopus_scooter.svg","png":"png/coverage__octopus_scooter.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__octopus_scooter.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__octopus_scooter.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__octopus_scooter.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"e09f8d69f6c921700d2cf0d4089e95ef80eb6652c09647f155208e44334c4673","png":"35b3080a914c64d0b0ac0a8e35834fa9785b803f4d4a6ee980db06582865d8b9"},"mediaStatus":"local"},{"id":"coverage__octopus_skateboard","task":"octopus_skateboard","subject":"octopus","vehicle":"skateboard","expected_wheels":2,"held_out":true,"reward":0.7875000000000001,"structure_score":0.8571428571428571,"semantic_score":0.75,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A purple octopus with large eyes is holding an orange and yellow striped object against a light blue background.","svg":"svg/coverage__octopus_skateboard.svg","png":"png/coverage__octopus_skateboard.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__octopus_skateboard.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__octopus_skateboard.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__octopus_skateboard.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"3478935b8784079471e0eb61b1539e4c0036aa4206c4c85c6b302d2619ae68ad","png":"2ccaf458d73605a7a063abf44dcd7d06050d155e47d8b4480f7137505d73808c"},"mediaStatus":"local"},{"id":"coverage__hedgehog_bicycle","task":"hedgehog_bicycle","subject":"hedgehog","vehicle":"bicycle","expected_wheels":2,"held_out":true,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon hedgehog is riding a red bicycle on a road under a blue sky with clouds and a sun.","svg":"svg/coverage__hedgehog_bicycle.svg","png":"png/coverage__hedgehog_bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__hedgehog_bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"50faf4487d8febd08d970a21aa2a0db25856a07f8005cd21d2c297bedf4639c8","png":"2c12f238d49419a240f7f962c6a81a0c5d46defa123aee3b739a2687819a0df0"},"mediaStatus":"local"},{"id":"coverage__hedgehog_unicycle","task":"hedgehog_unicycle","subject":"hedgehog","vehicle":"unicycle","expected_wheels":1,"held_out":true,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon hedgehog is riding a unicycle on a grassy field with colorful objects floating in the background.","svg":"svg/coverage__hedgehog_unicycle.svg","png":"png/coverage__hedgehog_unicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__hedgehog_unicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_unicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_unicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"f1f3297e5aa9d28442e018ad8e8df9825481da6532f581f02c7cb7e0221e05d0","png":"69d386a8d98781f360b874469acfd74e93399f41f4a9d6a9dc32dbe4389b124b"},"mediaStatus":"local"},{"id":"coverage__hedgehog_tandem-bicycle","task":"hedgehog_tandem-bicycle","subject":"hedgehog","vehicle":"tandem bicycle","expected_wheels":2,"held_out":true,"reward":0.36171875,"structure_score":0.7142857142857143,"semantic_score":0.171875,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"Two hedgehogs are riding a tandem bicycle on a simple road with clouds in the sky.","svg":"svg/coverage__hedgehog_tandem-bicycle.svg","png":"png/coverage__hedgehog_tandem-bicycle.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__hedgehog_tandem-bicycle.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_tandem-bicycle.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_tandem-bicycle.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"095def708ca895b4acce072cfa1dc64f83162fb0a8cdcdf2ee427f9a8cda4d4f","png":"52576d623d6111e85ea282356604d717f80f51f927a4cc32bad6e0a424e7394b"},"mediaStatus":"local"},{"id":"coverage__hedgehog_scooter","task":"hedgehog_scooter","subject":"hedgehog","vehicle":"scooter","expected_wheels":2,"held_out":true,"reward":1.0,"structure_score":1.0,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon hedgehog wearing a yellow helmet and goggles is riding a scooter with a light blue background and clouds.","svg":"svg/coverage__hedgehog_scooter.svg","png":"png/coverage__hedgehog_scooter.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__hedgehog_scooter.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_scooter.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_scooter.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"f5da46d52be6650b63a46a3fc4010012ed0bb7ff494740bc2988f1e62f5fbc56","png":"1fa63cceffb647b90466909a2ceb37063aee3960347e01371b908a05fc308712"},"mediaStatus":"local"},{"id":"coverage__hedgehog_skateboard","task":"hedgehog_skateboard","subject":"hedgehog","vehicle":"skateboard","expected_wheels":2,"held_out":true,"reward":0.95,"structure_score":0.8571428571428571,"semantic_score":1.0,"gate_passed":true,"judge_model":"Qwen/Qwen2.5-VL-72B-Instruct","judge_blind_caption":"A cartoon hedgehog is riding a red skateboard under a blue sky with a yellow sun and white clouds.","svg":"svg/coverage__hedgehog_skateboard.svg","png":"png/coverage__hedgehog_skateboard.png","config":"coverage","missingSourceFields":["model","access","provider","sample","violations"],"model":null,"access":null,"provider":null,"sample":null,"violations":null,"sourceUrl":"https://huggingface.co/datasets/sergiopaniego/pelican-svg-drawings/blob/548f58a232c4aadf05f4798c2d69b8bd95e4b502/svg/coverage__hedgehog_skateboard.svg","localSvg":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_skateboard.svg","localPng":"/media/benchmark/openenv-2026-07-29/coverage__hedgehog_skateboard.png","latency":null,"tags":["benchmark","benchmark-catalogue"],"sha256":{"svg":"a49b57e46f6b3ff5992b9ffed12efdee8f52b91809d1c7539186cf5e8fa26f38","png":"253c54a68f1aef94d037d7246b8f0fd96d58d04c7385a26ddb019a59d4102543"},"mediaStatus":"local"}]}