ChessBench — Pin
Games · 2026-03-22
ChessBench Pin contains 30 fixed non-mating Lichess tactics labeled with the pin theme. Models are scored only when their returned UCI move line exactly matches the expected line; the track is evenly stratified across three puzzle-rating buckets.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3.8 Flash | 70.0 |
| Gemini 4 Argon | 70.0 |
| GPT-6.1 Sol | 66.7 |
| Claude Opus 5.5 | 60.0 |
| GPT-6 Sol | 50.0 |
| Claude Fable 5.1 | 40.0 |
| Gemini 3 Flash Preview | 40.0 |
| Claude Haiku 5.5 | 16.7 |
| Claude Sonnet 5.5 | 16.7 |
| Grok 4.6 | 16.7 |
| GPT-6 Luna | 10.0 |
| Haiku 4.5 | 0.0 |