Skip to main content
Evaluation sources/Chess Puzzles
ParticipatingReasoning

Chess Puzzles

Epoch AI · Public model evaluation results from Chess Puzzles.

Official evaluation
Source description

This source measures concrete delivery performance in Reasoning; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

GPT-6 Astra0.7483.52026-11-05
GPT-6.1 Sol0.6878.22026-11-05
Claude Opus 5.50.6777.42026-11-05
Claude Opus 5.50.6777.42026-10-18
Claude Opus 5.50.6777.42026-10-17
GPT-5.50.6373.82026-11-05
GPT-5.5 Pro0.6273.02026-10-17
GPT-5.5 Pro0.6273.02026-11-05
GPT-5.5 Pro0.6273.02026-10-18
GPT-5.2 Pro0.671.22026-10-18
GPT-5.2 Pro0.671.22026-11-05
GPT-5.2 Pro0.671.22026-10-17
GPT-5.4 Pro0.5970.32026-11-05
GPT-5.6 Sol0.5970.32026-11-05
Claude Sonnet 5.50.5970.32026-10-17
Claude Sonnet 5.50.5970.32026-10-18
Claude Sonnet 5.50.5970.32026-11-05
Gemini 4 Argon0.5970.32026-11-05
Gemini 4 Argon0.5970.32026-10-18
Gemini 4 Argon0.5970.32026-10-17
Gemini 3.8 Flash0.5869.52026-11-05
GPT-6 Sol0.5667.72026-10-17
GPT-6 Sol0.5667.72026-11-05
GPT-6 Sol0.5667.72026-10-18
Claude Haiku 5.50.5566.82026-10-17
Claude Haiku 5.50.5566.82026-10-18
Claude Haiku 5.50.5566.82026-11-05
Claude Opus 4.80.5264.22026-11-05
Gemini 3.1 Pro Preview0.5163.32026-11-05
GPT-5 Pro0.4860.72026-10-18
GPT-5 Pro0.4860.72026-10-17
GPT-5 Pro0.4860.72026-11-05
GPT-5.20.4860.72026-11-05
GPT-5.40.4860.72026-11-05
Claude Fable 5.10.4860.72026-11-05
DeepSeek V4.1 Flash0.4860.72026-10-17
DeepSeek V4.1 Flash0.4860.72026-10-18
DeepSeek V4.1 Flash0.4860.72026-11-05
Claude Fable 50.4759.82026-11-05
GPT-5.6 Terra0.4759.82026-11-05
Qwen3.8 Max0.4658.92026-11-05
DeepSeek V4 Pro 08130.4658.92026-11-05
DeepSeek V4.1 Flash 10170.4658.92026-11-05
Claude Sonnet 50.4558.12026-11-05
GPT-5.6 Luna0.4356.32026-11-05
Claude Opus 50.4356.32026-11-05
Gemini 3.6 Flash0.4255.42026-11-05
Claude Opus 4.70.4154.52026-11-05
Grok 4.70.4154.52026-11-05
Gemini 3 Flash Preview0.453.72026-11-05
o30.3751.02026-11-05
Kimi K30.3751.02026-11-05
Muse Spark 1.30.3751.02026-11-05
GLM 5.30.3751.02026-11-05
GPT-50.3650.22026-11-05
GPT-6 Luna0.3650.22026-11-05
Grok 4.50.3549.32026-11-05
Muse Spark 1.10.3448.42026-11-05
Muse Spark 1.10.3448.42026-10-18
Muse Spark 1.10.3448.42026-10-17
Grok 4.60.3347.52026-11-05
Mistral Large 40.3347.52026-10-18
Mistral Large 40.3347.52026-10-17
DeepSeek V4 Flash 07310.3246.62026-11-05
Gemini 3 Pro Preview0.3145.82026-10-12
Grok 4.200.2944.02026-11-05
Mistral Large 40.2944.02026-11-05
Qwen3.7 Max0.2742.32026-11-05
Muse Spark 1.20.2742.32026-11-05
Muse Spark 1.20.2742.32026-10-17
Muse Spark 1.20.2742.32026-10-18
Qwen3.6 35B-A3B0.2641.42026-10-12
Gemini 3.1 Flash Lite0.2540.52026-10-12
GPT-5 mini0.2439.62026-11-05
Qwen3.7 Plus0.2439.62026-10-12
Claude Sonnet 4.60.2338.82026-11-05
GPT-5.4 mini0.2338.82026-11-05
Qwen3.7 Flash0.2338.82026-10-12
o4-mini0.2237.92026-11-05
GPT-5 nano0.2237.92026-11-05
Qwen3.6 27B0.2237.92026-10-12
GLM-5.20.2237.92026-11-05
GLM-4.70.2137.02026-11-05
Claude Opus 4.60.2137.02026-11-05
Inkling0.2137.02026-11-05
Gemini 3.5 Flash Lite0.2137.02026-11-05
GLM-5.3 Flash0.2137.02026-10-18
GLM-5.3 Flash0.2137.02026-11-05
GLM-5.3 Flash0.2137.02026-10-17
Gemini 2.5 Pro0.236.12026-10-12
gpt-oss-120b0.236.12026-10-12
GLM-5.10.236.12026-11-05
Qwen3.6 Max Preview0.236.12026-10-12
Kimi K2.60.236.12026-11-05
Inkling Small0.1834.42026-10-12
MiniMax-M30.1733.52026-11-05
Qwen3.6 Plus0.1632.62026-11-05
o3 Mini High0.1531.72026-11-05
Claude Opus 4.50.1430.92026-11-05
DeepSeek V3.20.1430.92026-10-12
Qwen3.5-Flash0.1430.92026-11-05
Kimi K2.7 Code0.1430.92026-11-05
o4 Mini High0.1330.02026-11-05
Qwen3.5 397B-A17B0.1330.02026-10-12
Qwen3.5 9B0.1229.12026-10-12
Qwen3.6 Flash0.1229.12026-11-05
GPT-5.5 Instant0.1229.12026-10-12
o3-mini0.1128.22026-11-05
o10.127.32026-11-03
Claude Sonnet 4.50.127.32026-11-05
GLM-50.127.32026-10-12
Qwen3.5 35B-A3B0.127.32026-10-12
Qwen3.5 Plus0.0926.52026-11-05
Claude Haiku 4.50.0825.62026-11-05
Gemma 4 26B A4B IT0.0623.82026-10-12
Qwen3 32B0.0523.02026-10-12
Qwen3 8B0.0523.02026-10-12
Qwen3 30B A3B0.0422.12026-10-12
Qwen3 14B0.0422.12026-10-12
gpt-oss-20b0.0422.12026-10-12
Qwen3 Max0.0422.12026-10-12
Phi 40.0119.42026-10-12
Mistral Small 3018.62026-10-12
Gemma 3 27B018.62026-10-12
Gemma 3 4B018.62026-10-12
Gemma 3 12B018.62026-10-12

Frequently asked questions