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
51GPT 5.4medium· Epoch AI Benchmarking Hub data37%
52Kimi K3high· Epoch AI Benchmarking Hub data37%
53Muse Spark 1.3max· Epoch AI Benchmarking Hub data37%
54OpenAI o3medium· Epoch AI Benchmarking Hub data37%
55Claude Opus 4.7xhigh· Epoch AI Benchmarking Hub data36%
56GPT 5high· Epoch AI Benchmarking Hub data36%
57GPT 5.2medium· Epoch AI Benchmarking Hub data36%
58GPT 5.4 Nanohigh· Epoch AI Benchmarking Hub data36%
59GPT-6 Lunamax· Epoch AI Benchmarking Hub data36%
60Kimi K3max· Epoch AI Benchmarking Hub data36%
61OpenAI o3high· Epoch AI Benchmarking Hub data36%
62OpenAI o3low· Epoch AI Benchmarking Hub data36%
63Grok 4.5high· Epoch AI Benchmarking Hub data35%
64Claude Sonnet 5xhigh· Epoch AI Benchmarking Hub data34%
65Muse Spark 1.1xhigh· Epoch AI Benchmarking Hub data34%
66Muse Spark 1.3xhigh· Epoch AI Benchmarking Hub data34%
67Grok 4.6· Epoch AI Benchmarking Hub data33%
68Mistral Large 4high· Epoch AI Benchmarking Hub data33%
69DeepSeek V4 Flash 0731max· Epoch AI Benchmarking Hub data32%
70GPT 5medium· Epoch AI Benchmarking Hub data32%
71Claude Fable 5low· Epoch AI Benchmarking Hub data31%
72GPT-5.6 Sollow· Epoch AI Benchmarking Hub data31%
73GPT 5.5low· Epoch AI Benchmarking Hub data30%
74Claude Opus 4.8low· Epoch AI Benchmarking Hub data29%
75Gemini 3.6 Flashminimal· Epoch AI Benchmarking Hub data29%
76Grok 4.20reasoning, 0309· Epoch AI Benchmarking Hub data29%
77Claude Opus 5low· Epoch AI Benchmarking Hub data27%
78Gemini 3.5 Flashminimal· Epoch AI Benchmarking Hub data27%
79GPT 5low· Epoch AI Benchmarking Hub data27%
80GPT-5.6 Terralow· Epoch AI Benchmarking Hub data27%
81Muse Spark 1.2xhigh· Epoch AI Benchmarking Hub data27%
82Qwen3.7 Max· Epoch AI Benchmarking Hub data27%
83Claude Opus 4.7low· Epoch AI Benchmarking Hub data26%
84Doubao Seed 2.1 Turbohigh· Epoch AI Benchmarking Hub data26%
85GPT 5.2low· Epoch AI Benchmarking Hub data26%
86Claude Haiku 5.5low· Epoch AI Benchmarking Hub data24%
87GPT-5 minihigh· Epoch AI Benchmarking Hub data24%
88Claude Sonnet 4.6max· Epoch AI Benchmarking Hub data23%
89GPT 5.1low· Epoch AI Benchmarking Hub data23%
90GPT-5.4 minihigh· Epoch AI Benchmarking Hub data23%
91GLM 5.2max· Epoch AI Benchmarking Hub data22%
92GPT-5 nanohigh· Epoch AI Benchmarking Hub data22%
93o4 Minimedium· Epoch AI Benchmarking Hub data22%
94Claude Opus 4.6max· Epoch AI Benchmarking Hub data21%
95Doubao Seed 2.1 Prohigh· Epoch AI Benchmarking Hub data21%
96Gemini 3.5 Flash Litelow· Epoch AI Benchmarking Hub data21%
97GLM 4.7· Epoch AI Benchmarking Hub data21%
98GLM 5.3 Flashmax· Epoch AI Benchmarking Hub data21%
99Inkling FP4xhigh· Epoch AI Benchmarking Hub data21%
100Doubao Seed 2.0 Litehigh· Epoch AI Benchmarking Hub data20%

Showing 51–100 of 163 results.

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