Matches species words in original captions; no new image judging. Multiple labels and missing/unidentified captions remain in the denominator. Original captions are retained below.
Perfect upstream reward = 1
Upstream outputs, not a Pelican Map ranking · reward 1.000
A cartoon pelican is riding a red bicycle on a grassy path under a blue sky.
{
"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.",
"latency": 38.06,
"svg": "svg/gpt-5.6-sol__pelican_bicycle__002.svg",
"png": "png/gpt-5.6-sol__pelican_bicycle__002.png"
}
gpt-5.6-sol__pelican_bicycle__003
Upstream outputs, not a Pelican Map ranking · reward 0.838
A cartoon duck is riding a red bicycle on grass under a blue sky with clouds and a sun.
{
"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.",
"latency": 40.36,
"svg": "svg/gpt-5.6-sol__pelican_bicycle__003.svg",
"png": "png/gpt-5.6-sol__pelican_bicycle__003.png"
}
gpt-5.6-sol__pelican_bicycle__004
Upstream outputs, not a Pelican Map ranking · reward 0.919
A cartoon bird with an orange beak and legs is riding a blue bicycle.
{
"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.",
"latency": 37.22,
"svg": "svg/gpt-5.6-sol__pelican_bicycle__009.svg",
"png": "png/gpt-5.6-sol__pelican_bicycle__009.png"
}
gpt-5.6-sol__pelican_bicycle__010
Upstream outputs, not a Pelican Map ranking · reward 1.000
A cartoon pelican is riding a red bicycle with a yellow sun in the background.
{
"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.",
"latency": 35.3,
"svg": "svg/gpt-5.6-sol__pelican_bicycle__012.svg",
"png": "png/gpt-5.6-sol__pelican_bicycle__012.png"
}
gpt-5.6-sol__pelican_bicycle__013
Upstream outputs, not a Pelican Map ranking · reward 1.000
A cartoon pelican is riding a red bicycle under a sunny sky with grass below.
{
"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.",
"latency": 33.85,
"svg": "svg/gpt-5.6-sol__pelican_bicycle__017.svg",
"png": "png/gpt-5.6-sol__pelican_bicycle__017.png"
}
gpt-5.6-sol__pelican_bicycle__018
Upstream outputs, not a Pelican Map ranking · reward 1.000
A cartoon pelican is riding a red bicycle under a sunny sky with clouds.
