Source AI reference score: 3.74 ± 0.18
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 · 2026-10-25 · 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
- 2026-10-24
- Fixed prompt
Generate an SVG of a pelican riding a bicycle- Source rules
- Tihu ↗
10 model labels · 26 effort groups · 78 samples
Dates and model labels follow the source and are not independently authenticated.
GPT-5.6 Luna9 samples
Source AI reference score: 4.20 ± 0.40
Source AI reference score: 4.03 ± 0.40
Source AI reference score: 4.19 ± 0.63
Source AI reference score: 5.86 ± 0.86
Source AI reference score: 6.21 ± 0.88
Source AI reference score: 4.80 ± 0.41
Source AI reference score: 5.89 ± 1.12
Source AI reference score: 6.01 ± 0.30
GPT-5.6 Sol9 samples
Source AI reference score: 6.20 ± 0.84
Source AI reference score: 7.81 ± 0.36
Source AI reference score: 8.19 ± 0.27
Source AI reference score: 7.59 ± 0.73
Source AI reference score: 6.18 ± 0.25
Source AI reference score: 6.32 ± 0.36
Source AI reference score: 6.93 ± 0.21
Source AI reference score: 7.47 ± 0.92
Source AI reference score: 7.44 ± 0.65
GPT-5.6 Terra9 samples
Source AI reference score: 3.63 ± 0.43
Source AI reference score: 7.00 ± 1.14
Source AI reference score: 6.11 ± 0.17
Source AI reference score: 8.11 ± 0.42
Source AI reference score: 5.80 ± 0.58
Source AI reference score: 5.14 ± 0.34
Source AI reference score: 7.83 ± 0.40
Source AI reference score: 6.81 ± 0.53
Source AI reference score: 5.06 ± 0.59
GPT-6 Astra9 samples
Source AI reference score: 8.21 ± 0.45
Source AI reference score: 8.65 ± 0.20
Source AI reference score: 8.06 ± 0.39
Source AI reference score: 7.49 ± 0.56
Source AI reference score: 8.50 ± 0.12
Source AI reference score: 8.60 ± 0.00
Source AI reference score: 8.96 ± 0.08
Source AI reference score: 8.63 ± 0.17
Source AI reference score: 8.96 ± 0.28
GPT-6 Luna9 samples
Source AI reference score: 5.54 ± 0.77
Source AI reference score: 4.41 ± 0.54
Source AI reference score: 6.90 ± 0.64
Source AI reference score: 6.66 ± 0.36
Source AI reference score: 6.31 ± 0.81
Source AI reference score: 4.49 ± 0.23
Source AI reference score: 6.53 ± 0.56
Source AI reference score: 6.98 ± 0.64
Source AI reference score: 5.84 ± 0.18
GPT-6 Sol9 samples
Source AI reference score: 5.79 ± 0.68
Source AI reference score: 5.70 ± 0.15
Source AI reference score: 4.54 ± 0.16
Source AI reference score: 5.69 ± 0.78
Source AI reference score: 6.17 ± 0.78
Source AI reference score: 6.90 ± 0.56
Source AI reference score: 8.13 ± 0.92
Source AI reference score: 7.22 ± 1.18
Source AI reference score: 7.92 ± 0.64
GPT-6.1 Sol9 samples
Source AI reference score: 8.30 ± 0.24
Source AI reference score: 7.24 ± 0.65
Source AI reference score: 8.57 ± 0.20
Source AI reference score: 8.49 ± 0.17
Source AI reference score: 7.49 ± 0.20
Source AI reference score: 7.64 ± 0.20
Source AI reference score: 8.26 ± 0.73
Source AI reference score: 8.36 ± 0.57
Source AI reference score: 8.61 ± 0.21
Grok 4.53 samples
Grok 4.63 samples
Grok 4.79 samples
Source AI reference score: 3.61 ± 0.54
Source AI reference score: 3.91 ± 0.14
Source AI reference score: 3.85 ± 0.93
Source AI reference score: 7.11 ± 0.25
Source AI reference score: 7.78 ± 0.32
Source AI reference score: 5.13 ± 0.76
Source AI reference score: 7.98 ± 0.12
Source AI reference score: 8.61 ± 0.33
Source AI reference score: 6.53 ± 0.52
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.
