Skip to content

Benchmark

Chess Puzzles

Scores are percentages.

Models measured
93
Scores recorded
163
Sources
1
IQ weight
1.82

Score distribution

29.5%
Mean
27%
Median
19.6%
Std dev
5%
10th percentile
59%
90th percentile
0%
Min
0%83%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.82 for chat models, measured over 93 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101Doubao Seed 2.0 Prohigh· Epoch AI Benchmarking Hub data20%
102GLM 5.1· Epoch AI Benchmarking Hub data20%
103GPT 5.4 Nanolow· Epoch AI Benchmarking Hub data20%
104Kimi K2.6· Epoch AI Benchmarking Hub data20%
105Claude Opus 4.8none· Epoch AI Benchmarking Hub data19%
106Claude Sonnet 4.6high· Epoch AI Benchmarking Hub data19%
107DeepSeek V4 Promax· Epoch AI Benchmarking Hub data19%
108GLM 5.2none· Epoch AI Benchmarking Hub data19%
109GPT 5.4low· Epoch AI Benchmarking Hub data19%
110GLM 5.2low· Epoch AI Benchmarking Hub data18%
111Grok 4.3high· Epoch AI Benchmarking Hub data18%
112Kimi K3low· Epoch AI Benchmarking Hub data18%
113GPT-5.4 minixhigh· Epoch AI Benchmarking Hub data17%
114GPT-5.6 Lunalow· Epoch AI Benchmarking Hub data17%
115MiniMax M3· Epoch AI Benchmarking Hub data17%
116Claude Sonnet 4.6medium· Epoch AI Benchmarking Hub data16%
117DeepSeek V4 Prohigh· Epoch AI Benchmarking Hub data16%
118Gemini 3.5 Flash Litehigh· Epoch AI Benchmarking Hub data16%
119GPT-5 minilow· Epoch AI Benchmarking Hub data16%
120Qwen3.6 Plus· Epoch AI Benchmarking Hub data16%
121GPT-5 nanolow· Epoch AI Benchmarking Hub data15%
122o3 Minihigh· Epoch AI Benchmarking Hub data15%
123o4 Minilow· Epoch AI Benchmarking Hub data15%
124Claude Opus 4.559k· Epoch AI Benchmarking Hub data14%
125Kimi K2.7 Code· Epoch AI Benchmarking Hub data14%
126Qwen3.5 Flash· Epoch AI Benchmarking Hub data14%
127o4 Minihigh· Epoch AI Benchmarking Hub data13%
128Qwen3.6 Flash· Epoch AI Benchmarking Hub data12%
129GPT 4.1· Epoch AI Benchmarking Hub data11%
130GPT 5minimal· Epoch AI Benchmarking Hub data11%
131o1low· Epoch AI Benchmarking Hub data11%
132o3 Minimedium· Epoch AI Benchmarking Hub data11%
133Claude Sonnet 4.532k· Epoch AI Benchmarking Hub data10%
134Claude Sonnet 4.559k· Epoch AI Benchmarking Hub data10%
135o1high· Epoch AI Benchmarking Hub data10%
136GPT 4o· Epoch AI Benchmarking Hub data9%
137GPT 5.5none· Epoch AI Benchmarking Hub data9%
138Qwen3.5 Plus· Epoch AI Benchmarking Hub data9%
139Claude Haiku 4.559k· Epoch AI Benchmarking Hub data8%
140MiniMax M3none· Epoch AI Benchmarking Hub data8%
141o1medium· Epoch AI Benchmarking Hub data8%
142Gemini 3.5 Flash Liteminimal· Epoch AI Benchmarking Hub data7%
143GPT-5.6 Solnone· Epoch AI Benchmarking Hub data7%
144Claude Sonnet 4.5· Epoch AI Benchmarking Hub data6%
145GPT 5.1none· Epoch AI Benchmarking Hub data6%
146o3 Minilow· Epoch AI Benchmarking Hub data6%
147Claude Haiku 4.532k· Epoch AI Benchmarking Hub data5%
148Claude Opus 4.5· Epoch AI Benchmarking Hub data5%
149Claude Opus 4.532k· Epoch AI Benchmarking Hub data5%
150Doubao-Seed 1.6· Epoch AI Benchmarking Hub data5%

Showing 101–150 of 163 results.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)