Skip to content

Benchmark

Ebr Bench

Scores are percentages.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
2.00

Score distribution

39.1%
Mean
34.3%
Median
27.7%
Std dev
7.9%
10th percentile
78.1%
90th percentile
2.4%
Min
2.4%92.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.00 for chat models, measured over 32 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-6.2 Astramax· Epoch AI Benchmarking Hub data92.4%
2Claude Fable 5.2max· Epoch AI Benchmarking Hub data90.5%
3Gemini 4 Carbonhigh· Epoch AI Benchmarking Hub data87.6%
4GPT-6.1 Terramax· Epoch AI Benchmarking Hub data78.1%
5GPT-6 Astramax· Epoch AI Benchmarking Hub data76.2%
6Claude Opus 5.5max· Epoch AI Benchmarking Hub data71.4%
7Gemini 4 Hydrogenxhigh· Epoch AI Benchmarking Hub data70.5%
8Gemini 4 Argonhigh· Epoch AI Benchmarking Hub data64.8%
9Claude Fable 5.1max· Epoch AI Benchmarking Hub data57.1%
10GPT-6.1 Solmax· Epoch AI Benchmarking Hub data54.3%
11GPT-6 Solmax· Epoch AI Benchmarking Hub data53.3%
12Claude Opus 5max· Epoch AI Benchmarking Hub data45.7%
13GPT-5.6 Solmax· Epoch AI Benchmarking Hub data44.8%
14Claude Haiku 5.5max· Epoch AI Benchmarking Hub data43.8%
15Claude Fable 5max· Epoch AI Benchmarking Hub data39.5%
16GPT 5.5xhigh· Epoch AI Benchmarking Hub data34.3%
17Muse Wonder 1.0max· Epoch AI Benchmarking Hub data31.4%
18Grok 4.6xhigh· Epoch AI Benchmarking Hub data30.5%
19Claude Opus 4.8max· Epoch AI Benchmarking Hub data28.6%
20GPT 5.4xhigh· Epoch AI Benchmarking Hub data25.4%
21GPT 5.2xhigh· Epoch AI Benchmarking Hub data23%
22Claude Opus 4.7max· Epoch AI Benchmarking Hub data19%
23Claude Opus 4.5128k· Epoch AI Benchmarking Hub data14.3%
24Gemini 3.1 Pro Preview· Epoch AI Benchmarking Hub data14.3%
25Claude Opus 4.6max· Epoch AI Benchmarking Hub data12.7%
26GPT 5high· Epoch AI Benchmarking Hub data12.7%
27GLM 5.2max· Epoch AI Benchmarking Hub data9.5%
28Qwen3.7 Max· Epoch AI Benchmarking Hub data9.5%
29Claude Opus 4.1· Epoch AI Benchmarking Hub data7.9%
30Gemini 3.5 Flashhigh· Epoch AI Benchmarking Hub data4.8%
31Claude Sonnet 4.5· Epoch AI Benchmarking Hub data2.4%
32Kimi K2.6· Epoch AI Benchmarking Hub data2.4%

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