Source AI reference score: 6.99 ± 0.49
Tihu · Pelican SVG benchmark
Browse Tihu source samples by model and effort; excluded from the main collection and timeline.
2026-11-08 · 2026-11-01 · 2026-10-26 · 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
- 2026-10-25
- Fixed prompt
Generate an SVG of a pelican riding a bicycle- Source rules
- Tihu ↗
27 model labels · 54 effort groups · 165 samples
Dates and model labels follow the source and are not independently authenticated.
Claude Opus 5.59 samples
Source AI reference score: 5.46 ± 0.27
Source AI reference score: 5.84 ± 0.32
Source AI reference score: 7.63 ± 0.42
Source AI reference score: 7.69 ± 0.62
Source AI reference score: 8.03 ± 0.45
Source AI reference score: 8.22 ± 0.95
Source AI reference score: 7.21 ± 0.56
Source AI reference score: 8.39 ± 0.48
Claude Sonnet 5.59 samples
Source AI reference score: 6.38 ± 0.39
Source AI reference score: 5.20 ± 0.30
Source AI reference score: 5.54 ± 0.55
Source AI reference score: 4.85 ± 0.47
Source AI reference score: 6.46 ± 0.14
Source AI reference score: 5.50 ± 0.57
Source AI reference score: 6.81 ± 0.44
Source AI reference score: 6.19 ± 0.32
Source AI reference score: 6.89 ± 0.65
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: 5.92 ± 0.26
Source AI reference score: 4.03 ± 0.26
Source AI reference score: 5.13 ± 0.35
Source AI reference score: 5.88 ± 0.90
Source AI reference score: 5.82 ± 0.66
Source AI reference score: 6.48 ± 0.70
GLM 5.33 samples
GLM 5.3 Flash3 samples
GPT-5.6 Luna10 samples
Source AI reference score: 4.10 ± 0.81
Source AI reference score: 4.19 ± 0.20
low · Sample 3/4
Tihu marked this sample invalid because text was returned instead of a drawing.
Source AI reference score: 4.88 ± 0.67
Source AI reference score: 4.61 ± 0.43
Source AI reference score: 5.31 ± 1.06
Source AI reference score: 3.88 ± 0.46
Source AI reference score: 5.80 ± 0.58
Source AI reference score: 5.60 ± 1.01
Source AI reference score: 5.53 ± 0.22
GPT-5.6 Sol9 samples
Source AI reference score: 5.69 ± 0.72
Source AI reference score: 5.67 ± 0.62
Source AI reference score: 7.07 ± 1.21
Source AI reference score: 6.59 ± 0.50
Source AI reference score: 7.04 ± 0.77
Source AI reference score: 5.32 ± 0.75
Source AI reference score: 8.84 ± 0.08
Source AI reference score: 7.97 ± 0.62
Source AI reference score: 6.67 ± 0.42
GPT-5.6 Terra10 samples
Source AI reference score: 5.38 ± 1.02
Source AI reference score: 6.89 ± 0.59
Source AI reference score: 4.61 ± 0.05
Source AI reference score: 7.29 ± 0.78
Source AI reference score: 5.85 ± 0.82
Source AI reference score: 6.28 ± 0.39
Source AI reference score: 6.77 ± 0.83
Source AI reference score: 7.05 ± 0.57
max · Sample 3/4
Tihu marked this sample invalid because text was returned instead of a drawing.
Source AI reference score: 7.86 ± 0.46
GPT-6 Astra9 samples
Source AI reference score: 8.20 ± 0.39
Source AI reference score: 8.31 ± 0.42
Source AI reference score: 8.20 ± 0.57
Source AI reference score: 8.70 ± 0.12
Source AI reference score: 8.64 ± 0.08
Source AI reference score: 7.31 ± 0.36
Source AI reference score: 8.36 ± 0.58
Source AI reference score: 8.94 ± 0.09
Source AI reference score: 9.07 ± 0.09
GPT-6 Luna9 samples
Source AI reference score: 3.91 ± 0.33
Source AI reference score: 4.56 ± 0.69
Source AI reference score: 4.38 ± 0.55
Source AI reference score: 5.30 ± 1.12
Source AI reference score: 4.58 ± 0.36
Source AI reference score: 6.21 ± 0.32
Source AI reference score: 6.15 ± 0.76
Source AI reference score: 7.26 ± 0.35
Source AI reference score: 7.30 ± 1.02
GPT-6 Sol9 samples
Source AI reference score: 5.46 ± 0.19
Source AI reference score: 5.56 ± 0.59
Source AI reference score: 5.56 ± 0.59
Source AI reference score: 6.18 ± 0.62
Source AI reference score: 6.30 ± 1.05
Source AI reference score: 6.30 ± 0.71
Source AI reference score: 8.78 ± 0.10
Source AI reference score: 7.79 ± 0.40
Source AI reference score: 8.63 ± 0.26
GPT-6.1 Sol9 samples
Source AI reference score: 8.39 ± 0.42
Source AI reference score: 7.89 ± 0.45
Source AI reference score: 8.41 ± 0.21
Source AI reference score: 6.84 ± 0.96
Source AI reference score: 6.54 ± 0.81
Source AI reference score: 8.46 ± 0.27
Source AI reference score: 8.65 ± 0.70
Source AI reference score: 8.79 ± 0.08
Source AI reference score: 8.15 ± 0.39
Gemini 3.1 Pro3 samples
Gemini 3.8 Flash9 samples
Source AI reference score: 8.53 ± 0.42
Source AI reference score: 8.31 ± 0.34
Source AI reference score: 7.90 ± 0.50
Source AI reference score: 8.22 ± 0.72
Source AI reference score: 8.17 ± 1.69
Source AI reference score: 8.90 ± 0.16
Source AI reference score: 8.30 ± 0.49
Source AI reference score: 8.78 ± 0.37
Source AI reference score: 8.99 ± 0.23
Gemini 4 Argon9 samples
Source AI reference score: 8.58 ± 0.23
Source AI reference score: 8.06 ± 0.75
Source AI reference score: 8.54 ± 0.38
Source AI reference score: 8.78 ± 0.23
Source AI reference score: 8.75 ± 0.35
Source AI reference score: 8.78 ± 0.18
Source AI reference score: 8.63 ± 0.51
Source AI reference score: 8.88 ± 0.14
Source AI reference score: 8.97 ± 0.25
Grok 4.53 samples
Grok 4.63 samples
Grok 4.710 samples
Source AI reference score: 4.63 ± 0.51
Source AI reference score: 3.56 ± 0.51
low · Sample 3/4
Tihu marked this sample invalid because text was returned instead of a drawing.
Source AI reference score: 5.95 ± 0.50
Source AI reference score: 6.38 ± 0.60
Source AI reference score: 6.61 ± 0.51
Source AI reference score: 5.06 ± 0.34
Source AI reference score: 6.09 ± 0.86
Source AI reference score: 7.80 ± 0.70
Source AI reference score: 7.09 ± 0.73
Hy33 samples
Kimi K39 samples
Source AI reference score: 4.89 ± 0.71
Source AI reference score: 4.93 ± 0.50
Source AI reference score: 5.97 ± 0.67
Source AI reference score: 6.52 ± 0.26
Source AI reference score: 6.65 ± 0.40
Source AI reference score: 7.33 ± 0.54
Source AI reference score: 7.49 ± 0.47
Source AI reference score: 8.08 ± 0.74
Source AI reference score: 7.63 ± 0.98
MiniMax-M33 samples
Qwen3.8-Flash3 samples
Qwen3.8-Max3 samples
No matching samples.
Source terms and archival notes
Tihu licenses test records/commentary under CC BY 4.0 and states that SVG images follow each vendor’s terms. Tihu attribution, source links and test dates are preserved; the record license is not extended to all SVGs.
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.
