Skip to content

Benchmark

Proofbench

Scores are percentages.

Models measured
83
Scores recorded
84
Sources
1
IQ weight
2.12

Score distribution

41.9%
Mean
36%
Median
31.7%
Std dev
5%
10th percentile
95%
90th percentile
0%
Min
0%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.12 for chat models, measured over 83 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51MiMo V2.5 Pro· Epoch AI Benchmarking Hub data22%
52GLM 5.3 Flashmax· Epoch AI Benchmarking Hub data21%
53GPT-5.4 minixhigh· Epoch AI Benchmarking Hub data21%
54Gemini 3 Pro Preview· Epoch AI Benchmarking Hub data20%
55Claude Sonnet 4.5· Epoch AI Benchmarking Hub data19%
56GPT 5high· Epoch AI Benchmarking Hub data18%
57MiniMax M3· Epoch AI Benchmarking Hub data18%
58Muse Spark· Epoch AI Benchmarking Hub data17%
59DeepSeek V4 Promax· Epoch AI Benchmarking Hub data16%
60Kimi K2.6· Epoch AI Benchmarking Hub data16%
61MiMo V2.5· Epoch AI Benchmarking Hub data16%
62Qwen 3.8 27B· Epoch AI Benchmarking Hub data16%
63Gemini 3 Flash· Epoch AI Benchmarking Hub data15%
64GPT 5.2xhigh· Epoch AI Benchmarking Hub data15%
65Grok 4.20reasoning, 0309· Epoch AI Benchmarking Hub data14%
66Gemini 3.5 Flash Lite· Epoch AI Benchmarking Hub data13%
67GPT-5 nanohigh· Epoch AI Benchmarking Hub data12%
68Grok 4.3high· Epoch AI Benchmarking Hub data11%
69Mistral Large 4· Epoch AI Benchmarking Hub data10%
70GPT-5 minihigh· Epoch AI Benchmarking Hub data9%
71GPT-5.1 Codex Max· Epoch AI Benchmarking Hub data9%
72Mistral Medium2604· Epoch AI Benchmarking Hub data9%
73DeepSeek V3.2· Epoch AI Benchmarking Hub data8%
74GLM 4.7· Epoch AI Benchmarking Hub data6%
75Inkling Small· Epoch AI Benchmarking Hub data6%
76GPT 5.4 Nanohigh· Epoch AI Benchmarking Hub data5%
77Grok 4.1 Fastreasoning· Epoch AI Benchmarking Hub data4%
78MiniMax M2.5· Epoch AI Benchmarking Hub data4%
79Mercury 2.5· Epoch AI Benchmarking Hub data3%
80MiniMax M2.7· Epoch AI Benchmarking Hub data3%
81Nemotron 3 Ultra· Epoch AI Benchmarking Hub data2%
82Inkling FP4· Epoch AI Benchmarking Hub data0%
83Laguna M.1· Epoch AI Benchmarking Hub data0%
84Laguna XS.2· Epoch AI Benchmarking Hub data0%

Showing 51–84 of 84 results.

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