Source AI reference score: 5.96 ± 0.17
Tihu · Pelican SVG benchmark
Browse Tihu source samples by model and effort; excluded from the main collection and timeline.
2026-11-22 · 2026-11-08 · 2026-11-01 · 2026-10-26 · 2026-10-25 · 2026-10-24 · 2026-10-23 · 2026-10-22 · 2026-10-21 · 2026-10-20 · 2026-10-19 · 2026-10-18 · 2026-10-17 · 2026-10-16 · 2026-10-15 · 2026-10-14 · 2026-10-13 · 2026-10-12 · 2026-10-11 · 2026-10-10 · 2026-10-09 · 2026-10-08
Scores come from Tihu AI judges. This archive neither rescores the samples nor ranks models by them.
- Publisher
- Tihu ↗
- Test date
- 2026-11-15
- Fixed prompt
Generate an SVG of a pelican riding a bicycle- Source rules
- Tihu ↗
31 model labels · 62 effort groups · 188 samples
Dates and model labels follow the source and are not independently authenticated.
Claude Fable 5.29 samples
Source AI reference score: 6.96 ± 0.59
Source AI reference score: 6.64 ± 0.27
Source AI reference score: 6.99 ± 0.17
Source AI reference score: 6.66 ± 0.66
Source AI reference score: 7.00 ± 0.21
Source AI reference score: 8.81 ± 0.22
Source AI reference score: 8.54 ± 0.24
Source AI reference score: 7.96 ± 0.87
Claude Opus 5.59 samples
Source AI reference score: 6.63 ± 0.65
Source AI reference score: 6.56 ± 0.17
Source AI reference score: 6.19 ± 0.42
Source AI reference score: 8.55 ± 0.07
Source AI reference score: 8.63 ± 0.20
Source AI reference score: 7.60 ± 1.04
Source AI reference score: 8.53 ± 0.43
Source AI reference score: 8.10 ± 0.35
Source AI reference score: 7.95 ± 0.83
Claude Sonnet 5.59 samples
Source AI reference score: 5.49 ± 0.67
Source AI reference score: 5.11 ± 0.65
Source AI reference score: 5.13 ± 0.57
Source AI reference score: 5.46 ± 0.72
Source AI reference score: 6.07 ± 0.30
Source AI reference score: 5.59 ± 0.64
Source AI reference score: 6.14 ± 0.68
Source AI reference score: 8.32 ± 0.32
Source AI reference score: 7.65 ± 0.24
Composer 2.53 samples
DeepSeek V4 Pro3 samples
DeepSeek V4.1 Flash3 samples
Doubao Seed 2.1 Pro3 samples
GLM 5.26 samples
Source AI reference score: 4.73 ± 0.41
Source AI reference score: 4.66 ± 0.34
Source AI reference score: 5.55 ± 0.65
Source AI reference score: 6.20 ± 1.28
Source AI reference score: 6.91 ± 0.57
Source AI reference score: 7.76 ± 0.46
GLM 5.33 samples
GLM 5.3 Flash3 samples
GPT-5.6 Luna9 samples
Source AI reference score: 5.85 ± 0.40
Source AI reference score: 4.04 ± 0.25
Source AI reference score: 4.09 ± 0.27
Source AI reference score: 3.33 ± 0.37
Source AI reference score: 5.04 ± 0.31
Source AI reference score: 3.20 ± 0.35
Source AI reference score: 4.84 ± 0.38
Source AI reference score: 6.00 ± 0.87
Source AI reference score: 5.70 ± 0.44
GPT-5.6 Sol9 samples
Source AI reference score: 7.78 ± 0.70
Source AI reference score: 8.06 ± 0.06
Source AI reference score: 5.28 ± 0.33
Source AI reference score: 4.99 ± 0.61
Source AI reference score: 7.53 ± 0.53
Source AI reference score: 8.24 ± 0.55
Source AI reference score: 5.11 ± 0.87
Source AI reference score: 7.74 ± 1.11
Source AI reference score: 7.99 ± 0.31
GPT-5.6 Terra10 samples
Source AI reference score: 5.80 ± 0.42
low · Sample 2/4
Tihu marked this SVG invalid. See the source for the reported reason.
Source AI reference score: 8.03 ± 0.28
Source AI reference score: 7.49 ± 0.60
Source AI reference score: 5.75 ± 0.83
Source AI reference score: 6.09 ± 0.82
Source AI reference score: 4.11 ± 1.23
Source AI reference score: 7.60 ± 1.01
Source AI reference score: 7.11 ± 0.35
Source AI reference score: 5.75 ± 0.37
GPT-6 Astra9 samples
Source AI reference score: 7.58 ± 1.08
Source AI reference score: 7.76 ± 0.57
Source AI reference score: 8.86 ± 0.19
Source AI reference score: 8.01 ± 0.31
Source AI reference score: 7.71 ± 0.72
Source AI reference score: 7.10 ± 0.50
Source AI reference score: 9.01 ± 0.14
Source AI reference score: 8.88 ± 0.14
Source AI reference score: 8.78 ± 0.26
GPT-6 Luna9 samples
Source AI reference score: 6.19 ± 0.52
Source AI reference score: 5.84 ± 0.61
Source AI reference score: 4.69 ± 0.76
Source AI reference score: 6.58 ± 0.73
Source AI reference score: 5.34 ± 0.64
Source AI reference score: 5.55 ± 1.27
Source AI reference score: 7.30 ± 0.27
Source AI reference score: 6.41 ± 0.53
Source AI reference score: 6.66 ± 0.19
GPT-6 Sol9 samples
Source AI reference score: 5.03 ± 0.29
Source AI reference score: 7.61 ± 0.45
Source AI reference score: 5.99 ± 0.30
Source AI reference score: 7.65 ± 0.77
Source AI reference score: 7.33 ± 0.52
Source AI reference score: 7.34 ± 1.53
Source AI reference score: 8.47 ± 0.48
Source AI reference score: 7.75 ± 0.56
Source AI reference score: 8.28 ± 0.26
GPT-6.1 Sol9 samples
Source AI reference score: 8.26 ± 0.45
Source AI reference score: 7.10 ± 1.32
Source AI reference score: 8.49 ± 0.43
Source AI reference score: 8.25 ± 0.57
Source AI reference score: 8.03 ± 0.34
Source AI reference score: 8.36 ± 0.40
Source AI reference score: 8.74 ± 0.19
Source AI reference score: 9.00 ± 0.12
Source AI reference score: 8.65 ± 0.20
GPT-6.1 Terra9 samples
Source AI reference score: 6.29 ± 0.25
Source AI reference score: 5.86 ± 0.39
Source AI reference score: 5.97 ± 0.48
Source AI reference score: 6.26 ± 0.51
Source AI reference score: 5.42 ± 0.36
Source AI reference score: 5.03 ± 0.29
Source AI reference score: 8.44 ± 0.26
Source AI reference score: 7.04 ± 1.00
Source AI reference score: 7.59 ± 1.08
Gemini 3.1 Pro3 samples
Gemini 3.8 Flash10 samples
Source AI reference score: 6.26 ± 0.49
Source AI reference score: 8.42 ± 0.35
Source AI reference score: 7.23 ± 0.84
Source AI reference score: 8.32 ± 0.96
Source AI reference score: 7.90 ± 0.53
medium · Sample 3/4
Tihu marked this SVG invalid. See the source for the reported reason.
Source AI reference score: 7.05 ± 1.03
Source AI reference score: 8.03 ± 0.66
Source AI reference score: 4.48 ± 0.28
Source AI reference score: 7.53 ± 0.82
Gemini 4 Argon9 samples
Source AI reference score: 8.67 ± 0.35
Source AI reference score: 8.53 ± 0.59
Source AI reference score: 8.52 ± 0.27
Source AI reference score: 8.93 ± 0.28
Source AI reference score: 9.06 ± 0.19
Source AI reference score: 8.17 ± 0.72
Source AI reference score: 8.62 ± 0.20
Source AI reference score: 9.00 ± 0.13
Source AI reference score: 8.94 ± 0.09
Grok 4.53 samples
Grok 4.63 samples
Grok 4.79 samples
Source AI reference score: 3.94 ± 0.21
Source AI reference score: 5.22 ± 0.63
Source AI reference score: 4.42 ± 0.68
Source AI reference score: 5.67 ± 0.22
Source AI reference score: 5.14 ± 0.17
Source AI reference score: 5.40 ± 0.28
Source AI reference score: 8.38 ± 0.22
Source AI reference score: 7.08 ± 0.37
Source AI reference score: 6.89 ± 0.30
Hy33 samples
Kimi K39 samples
Source AI reference score: 6.68 ± 0.51
Source AI reference score: 6.79 ± 0.32
Source AI reference score: 4.97 ± 0.56
Source AI reference score: 6.65 ± 0.56
Source AI reference score: 5.08 ± 0.39
Source AI reference score: 5.67 ± 0.16
Source AI reference score: 6.32 ± 0.65
Source AI reference score: 8.45 ± 0.46
Source AI reference score: 8.78 ± 0.30
Kimi K3.1 Pro3 samples
MiniMax M3.1 Flash3 samples
MiniMax-M33 samples
Qwen3.8-Flash3 samples
Qwen3.8-Max3 samples
No matching samples.
Source terms and archival notes
Tihu licenses test records and judges’ commentary under CC BY 4.0. SVG images follow each model vendor’s terms. Tihu attribution, original sources and the data date are retained.
Original sample IDs, detail URLs, SVG files and former archive numbers are preserved. Current main-collection numbers remain derived from counted works. Further systematic evaluation batches belong in Benchmark.
