Evaluation sources/Chess Puzzles
ParticipatingReasoning
Chess Puzzles
Epoch AI · Public model evaluation results from Chess Puzzles.
Model results from this source
| Claude Fable 5.2 | 0.79 | 84.6 | 2026-11-10 |
| Gemini 4 Carbon | 0.78 | 83.8 | 2026-11-11 |
| GPT-6 Astra | 0.74 | 80.6 | 2026-11-05 |
| GPT-6.1 Sol | 0.68 | 75.7 | 2026-11-05 |
| Claude Opus 5.5 | 0.67 | 74.9 | 2026-11-05 |
| Claude Opus 5.5 | 0.67 | 74.9 | 2026-10-18 |
| Claude Opus 5.5 | 0.67 | 74.9 | 2026-10-17 |
| GPT-5.5 | 0.63 | 71.7 | 2026-11-05 |
| GPT-5.5 Pro | 0.62 | 70.9 | 2026-10-17 |
| GPT-5.5 Pro | 0.62 | 70.9 | 2026-11-05 |
| GPT-5.5 Pro | 0.62 | 70.9 | 2026-10-18 |
| GPT-5.2 Pro | 0.6 | 69.2 | 2026-10-18 |
| GPT-5.2 Pro | 0.6 | 69.2 | 2026-11-05 |
| GPT-5.2 Pro | 0.6 | 69.2 | 2026-10-17 |
| GPT-5.4 Pro | 0.59 | 68.4 | 2026-11-05 |
| GPT-5.6 Sol | 0.59 | 68.4 | 2026-11-05 |
| Claude Sonnet 5.5 | 0.59 | 68.4 | 2026-10-17 |
| Claude Sonnet 5.5 | 0.59 | 68.4 | 2026-10-18 |
| Claude Sonnet 5.5 | 0.59 | 68.4 | 2026-11-05 |
| Gemini 4 Argon | 0.59 | 68.4 | 2026-11-05 |
| Gemini 4 Argon | 0.59 | 68.4 | 2026-10-18 |
| Gemini 4 Argon | 0.59 | 68.4 | 2026-10-17 |
| Gemini 3.8 Flash | 0.58 | 67.6 | 2026-11-05 |
| GPT-6 Sol | 0.56 | 66.0 | 2026-10-17 |
| GPT-6 Sol | 0.56 | 66.0 | 2026-11-05 |
| GPT-6 Sol | 0.56 | 66.0 | 2026-10-18 |
| Claude Haiku 5.5 | 0.55 | 65.2 | 2026-10-17 |
| Claude Haiku 5.5 | 0.55 | 65.2 | 2026-10-18 |
| Claude Haiku 5.5 | 0.55 | 65.2 | 2026-11-05 |
| Claude Opus 4.8 | 0.52 | 62.8 | 2026-11-05 |
| Gemini 3.1 Pro Preview | 0.51 | 61.9 | 2026-11-05 |
| GPT-5 Pro | 0.48 | 59.5 | 2026-10-18 |
| GPT-5 Pro | 0.48 | 59.5 | 2026-10-17 |
| GPT-5 Pro | 0.48 | 59.5 | 2026-11-05 |
| GPT-5.2 | 0.48 | 59.5 | 2026-11-05 |
| GPT-5.4 | 0.48 | 59.5 | 2026-11-05 |
| Claude Fable 5.1 | 0.48 | 59.5 | 2026-11-05 |
| DeepSeek V4.1 Flash | 0.48 | 59.5 | 2026-10-17 |
| DeepSeek V4.1 Flash | 0.48 | 59.5 | 2026-10-18 |
| DeepSeek V4.1 Flash | 0.48 | 59.5 | 2026-11-05 |
| Claude Fable 5 | 0.47 | 58.7 | 2026-11-05 |
| GPT-5.6 Terra | 0.47 | 58.7 | 2026-11-05 |
| Qwen3.8 Max | 0.46 | 57.9 | 2026-11-05 |
| DeepSeek V4 Pro 0813 | 0.46 | 57.9 | 2026-11-05 |
| DeepSeek V4.1 Flash 1017 | 0.46 | 57.9 | 2026-11-05 |
| Claude Sonnet 5 | 0.45 | 57.1 | 2026-11-05 |
| Claude Opus 5 | 0.43 | 55.5 | 2026-11-05 |
| GPT-5.6 Luna | 0.43 | 55.5 | 2026-11-05 |
| Gemini 3.6 Flash | 0.42 | 54.7 | 2026-11-05 |
| Claude Opus 4.7 | 0.41 | 53.8 | 2026-11-05 |
| Grok 4.7 | 0.41 | 53.8 | 2026-11-05 |
| Gemini 3 Flash Preview | 0.4 | 53.0 | 2026-11-05 |
| Kimi K3 | 0.37 | 50.6 | 2026-11-05 |
| o3 | 0.37 | 50.6 | 2026-11-05 |
| Muse Spark 1.3 | 0.37 | 50.6 | 2026-11-05 |
| GLM 5.3 | 0.37 | 50.6 | 2026-11-05 |
| GPT-5 | 0.36 | 49.8 | 2026-11-05 |
| GPT-6 Luna | 0.36 | 49.8 | 2026-11-05 |
| Grok 4.5 | 0.35 | 49.0 | 2026-11-05 |
| Muse Spark 1.1 | 0.34 | 48.2 | 2026-11-05 |
| Muse Spark 1.1 | 0.34 | 48.2 | 2026-10-18 |
| Muse Spark 1.1 | 0.34 | 48.2 | 2026-10-17 |
| Mistral Large 4 | 0.33 | 47.4 | 2026-10-18 |
| Mistral Large 4 | 0.33 | 47.4 | 2026-10-17 |
| Grok 4.6 | 0.33 | 47.4 | 2026-11-05 |
| DeepSeek V4 Flash 0731 | 0.32 | 46.6 | 2026-11-05 |
| Gemini 3 Pro Preview | 0.31 | 45.7 | 2026-10-12 |
| Grok 4.20 | 0.29 | 44.1 | 2026-11-05 |
| Mistral Large 4 | 0.29 | 44.1 | 2026-11-05 |
| Qwen3.7 Max | 0.27 | 42.5 | 2026-11-05 |
| Muse Spark 1.2 | 0.27 | 42.5 | 2026-11-05 |
| Muse Spark 1.2 | 0.27 | 42.5 | 2026-10-17 |
| Muse Spark 1.2 | 0.27 | 42.5 | 2026-10-18 |
| Qwen3.6 35B-A3B | 0.26 | 41.7 | 2026-10-12 |
| Gemini 3.1 Flash Lite | 0.25 | 40.9 | 2026-10-12 |
| Qwen3.7 Plus | 0.24 | 40.1 | 2026-10-12 |
| GPT-5 mini | 0.24 | 40.1 | 2026-11-05 |
| Claude Sonnet 4.6 | 0.23 | 39.3 | 2026-11-05 |
| GPT-5.4 mini | 0.23 | 39.3 | 2026-11-05 |
| Qwen3.7 Flash | 0.23 | 39.3 | 2026-10-12 |
| Qwen3.6 27B | 0.22 | 38.5 | 2026-10-12 |
| GPT-5 nano | 0.22 | 38.5 | 2026-11-05 |
| o4-mini | 0.22 | 38.5 | 2026-11-05 |
| GLM-5.2 | 0.22 | 38.5 | 2026-11-05 |
| Claude Opus 4.6 | 0.21 | 37.6 | 2026-11-05 |
| Gemini 3.5 Flash Lite | 0.21 | 37.6 | 2026-11-05 |
| Inkling | 0.21 | 37.6 | 2026-11-05 |
| GLM-4.7 | 0.21 | 37.6 | 2026-11-05 |
| GLM-5.3 Flash | 0.21 | 37.6 | 2026-10-18 |
| GLM-5.3 Flash | 0.21 | 37.6 | 2026-11-05 |
| GLM-5.3 Flash | 0.21 | 37.6 | 2026-10-17 |
| Qwen3.6 Max Preview | 0.2 | 36.8 | 2026-10-12 |
| Gemini 2.5 Pro | 0.2 | 36.8 | 2026-10-12 |
| Kimi K2.6 | 0.2 | 36.8 | 2026-11-05 |
| gpt-oss-120b | 0.2 | 36.8 | 2026-10-12 |
| GLM-5.1 | 0.2 | 36.8 | 2026-11-05 |
| Inkling Small | 0.18 | 35.2 | 2026-10-12 |
| MiniMax-M3 | 0.17 | 34.4 | 2026-11-05 |
| Qwen3.6 Plus | 0.16 | 33.6 | 2026-11-05 |
| o3 Mini High | 0.15 | 32.8 | 2026-11-05 |
| Claude Opus 4.5 | 0.14 | 32.0 | 2026-11-05 |
| Kimi K2.7 Code | 0.14 | 32.0 | 2026-11-05 |
| Qwen3.5-Flash | 0.14 | 32.0 | 2026-11-05 |
| DeepSeek V3.2 | 0.14 | 32.0 | 2026-10-12 |
| Qwen3.5 397B-A17B | 0.13 | 31.2 | 2026-10-12 |
| o4 Mini High | 0.13 | 31.2 | 2026-11-05 |
| Qwen3.5 9B | 0.12 | 30.4 | 2026-10-12 |
| Qwen3.6 Flash | 0.12 | 30.4 | 2026-11-05 |
| GPT-5.5 Instant | 0.12 | 30.4 | 2026-10-12 |
| o1 | 0.11 | 29.5 | 2026-11-10 |
| o3-mini | 0.11 | 29.5 | 2026-11-05 |
| Qwen3.5 35B-A3B | 0.1 | 28.7 | 2026-10-12 |
| Claude Sonnet 4.5 | 0.1 | 28.7 | 2026-11-05 |
| o1 | 0.1 | 28.7 | 2026-11-03 |
| GLM-5 | 0.1 | 28.7 | 2026-10-12 |
| Qwen3.5 Plus | 0.09 | 27.9 | 2026-11-05 |
| Claude Haiku 4.5 | 0.08 | 27.1 | 2026-11-05 |
| o1 | 0.08 | 27.1 | 2026-11-10 |
| Gemma 4 26B A4B IT | 0.06 | 25.5 | 2026-10-12 |
| Qwen3 32B | 0.05 | 24.7 | 2026-10-12 |
| Qwen3 8B | 0.05 | 24.7 | 2026-10-12 |
| Qwen3 Max | 0.04 | 23.9 | 2026-10-12 |
| gpt-oss-20b | 0.04 | 23.9 | 2026-10-12 |
| Qwen3 30B A3B | 0.04 | 23.9 | 2026-10-12 |
| Qwen3 14B | 0.04 | 23.9 | 2026-10-12 |
| Phi 4 | 0.01 | 21.4 | 2026-10-12 |
| Gemma 3 4B | 0 | 20.6 | 2026-10-12 |
| Gemma 3 12B | 0 | 20.6 | 2026-10-12 |
| Gemma 3 27B | 0 | 20.6 | 2026-10-12 |
| Mistral Small 3 | 0 | 20.6 | 2026-10-12 |