Source AI reference score: 6.42 ± 0.34
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 · 2026-10-24 · 2026-10-23 · 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
- 2026-10-22
- 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: 5.39 ± 0.33
Source AI reference score: 5.54 ± 0.56
Source AI reference score: 3.67 ± 0.52
Source AI reference score: 4.01 ± 0.48
Source AI reference score: 3.50 ± 0.32
Source AI reference score: 4.81 ± 0.60
Source AI reference score: 5.86 ± 0.35
Source AI reference score: 5.91 ± 0.89
GPT-5.6 Sol9 samples
Source AI reference score: 6.90 ± 0.93
Source AI reference score: 7.68 ± 0.23
Source AI reference score: 7.25 ± 0.97
Source AI reference score: 6.40 ± 0.89
Source AI reference score: 8.00 ± 0.47
Source AI reference score: 6.40 ± 0.52
Source AI reference score: 8.75 ± 0.25
Source AI reference score: 6.69 ± 1.05
Source AI reference score: 5.39 ± 0.65
GPT-5.6 Terra9 samples
Source AI reference score: 6.30 ± 1.11
Source AI reference score: 6.00 ± 0.54
Source AI reference score: 8.09 ± 0.42
Source AI reference score: 6.00 ± 0.57
Source AI reference score: 6.67 ± 1.12
Source AI reference score: 6.34 ± 0.18
Source AI reference score: 8.46 ± 0.32
Source AI reference score: 7.13 ± 0.42
Source AI reference score: 7.11 ± 0.76
GPT-6 Astra9 samples
Source AI reference score: 6.94 ± 0.26
Source AI reference score: 6.96 ± 1.23
Source AI reference score: 7.06 ± 1.23
Source AI reference score: 8.63 ± 0.17
Source AI reference score: 7.14 ± 0.36
Source AI reference score: 7.25 ± 0.87
Source AI reference score: 8.64 ± 0.87
Source AI reference score: 8.10 ± 0.79
Source AI reference score: 8.71 ± 0.19
GPT-6 Luna9 samples
Source AI reference score: 5.38 ± 0.34
Source AI reference score: 5.69 ± 0.62
Source AI reference score: 7.25 ± 1.02
Source AI reference score: 8.10 ± 0.43
Source AI reference score: 7.10 ± 0.98
Source AI reference score: 7.74 ± 0.59
Source AI reference score: 6.05 ± 0.39
Source AI reference score: 6.77 ± 0.54
Source AI reference score: 6.70 ± 0.97
GPT-6 Sol9 samples
Source AI reference score: 4.64 ± 0.28
Source AI reference score: 8.04 ± 0.31
Source AI reference score: 7.14 ± 1.58
Source AI reference score: 6.96 ± 0.64
Source AI reference score: 7.01 ± 0.63
Source AI reference score: 6.18 ± 0.64
Source AI reference score: 7.08 ± 0.85
Source AI reference score: 7.26 ± 0.78
Source AI reference score: 7.49 ± 0.34
GPT-6.1 Sol9 samples
Source AI reference score: 7.48 ± 0.15
Source AI reference score: 7.40 ± 0.79
Source AI reference score: 7.05 ± 0.87
Source AI reference score: 6.46 ± 0.62
Source AI reference score: 8.28 ± 0.38
Source AI reference score: 7.45 ± 0.90
Source AI reference score: 7.90 ± 0.89
Source AI reference score: 8.78 ± 0.17
Source AI reference score: 8.13 ± 0.98
Grok 4.53 samples
Grok 4.63 samples
Grok 4.79 samples
Source AI reference score: 4.90 ± 0.78
Source AI reference score: 4.64 ± 0.44
Source AI reference score: 5.59 ± 1.17
Source AI reference score: 6.00 ± 0.47
Source AI reference score: 4.94 ± 0.63
Source AI reference score: 4.71 ± 0.32
Source AI reference score: 8.02 ± 0.24
Source AI reference score: 7.90 ± 0.30
Source AI reference score: 4.71 ± 0.85
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.
