Skip to content

Benchmark

Lmca

Scores are percentages.

Models measured
141
Scores recorded
205
Sources
1
IQ weight
1.56

Score distribution

41.6%
Mean
44.5%
Median
18.1%
Std dev
15.2%
10th percentile
64.8%
90th percentile
2.8%
Min
2.8%70.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.56 for chat models, measured over 141 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Fable 5.2xhigh· Epoch AI Benchmarking Hub data70.6%
2Claude Fable 5.2· Epoch AI Benchmarking Hub data70.1%
3Claude Fable 5.2medium· Epoch AI Benchmarking Hub data70%
4Claude Fable 5.2high· Epoch AI Benchmarking Hub data69.9%
5Claude Fable 5.2low· Epoch AI Benchmarking Hub data69.6%
6Claude Sonnet 5.5max· Epoch AI Benchmarking Hub data68.3%
7Claude Opus 5.5max· Epoch AI Benchmarking Hub data68.2%
8Claude Sonnet 5.5xhigh· Epoch AI Benchmarking Hub data66.3%
9Claude Opus 5.5xhigh· Epoch AI Benchmarking Hub data66.2%
10Claude Sonnet 5.5high· Epoch AI Benchmarking Hub data65.9%
11Claude Opus 5.5high· Epoch AI Benchmarking Hub data65.9%
12Gemini 4 Carbonmedium· Epoch AI Benchmarking Hub data65.7%
13Claude Opus 5.5medium· Epoch AI Benchmarking Hub data65.7%
14Claude Fable 5.1· Epoch AI Benchmarking Hub data65.5%
15Claude Sonnet 5.5medium· Epoch AI Benchmarking Hub data65.5%
16Gemini 4 Carbonlow· Epoch AI Benchmarking Hub data65.4%
17Claude Fable 5.1medium· Epoch AI Benchmarking Hub data65.3%
18Claude Fable 5.1high· Epoch AI Benchmarking Hub data65.1%
19Claude Fable 5.1xhigh· Epoch AI Benchmarking Hub data65.1%
20Claude Opus 5.5low· Epoch AI Benchmarking Hub data64.9%
21Gemini 4 Carbon· Epoch AI Benchmarking Hub data64.8%
22Claude Sonnet 5.5low· Epoch AI Benchmarking Hub data64.5%
23Claude Opus 5xhigh· Epoch AI Benchmarking Hub data64.5%
24GPT-6 Astraxhigh· Epoch AI Benchmarking Hub data64.4%
25GPT-6 Astra· Epoch AI Benchmarking Hub data64.1%
26GPT-6 Astrahigh· Epoch AI Benchmarking Hub data63.8%
27Gemini 4 Argonhigh· Epoch AI Benchmarking Hub data63.7%
28Claude Opus 5high· Epoch AI Benchmarking Hub data63.7%
29Claude Fable 5.1low· Epoch AI Benchmarking Hub data63.5%
30Claude Opus 5max· Epoch AI Benchmarking Hub data63.3%
31Claude Opus 5medium· Epoch AI Benchmarking Hub data62.9%
32GPT-6 Astramedium· Epoch AI Benchmarking Hub data62.9%
33Gemini 4 Argonlow· Epoch AI Benchmarking Hub data62.9%
34Gemini 4 Argonmedium· Epoch AI Benchmarking Hub data62.9%
35GPT-6.1 Solmax· Epoch AI Benchmarking Hub data62.8%
36Claude Opus 5low· Epoch AI Benchmarking Hub data62.6%
37GPT-6 Astralow· Epoch AI Benchmarking Hub data62.2%
38Claude Fable 5high· Epoch AI Benchmarking Hub data61.1%
39Claude Fable 5xhigh· Epoch AI Benchmarking Hub data61%
40Claude Fable 5max· Epoch AI Benchmarking Hub data60.3%
41Claude Fable 5medium· Epoch AI Benchmarking Hub data60.3%
42Claude Fable 5low· Epoch AI Benchmarking Hub data59.6%
43GPT-5.6 Solpro / max· Epoch AI Benchmarking Hub data59.2%
44GPT-6 Solmax· Epoch AI Benchmarking Hub data59.1%
45GPT-5.6 Solxhigh· Epoch AI Benchmarking Hub data58.5%
46GPT-5.6 Solmax· Epoch AI Benchmarking Hub data58.4%
47Kimi K3.1 Promax· Epoch AI Benchmarking Hub data57.6%
48Claude Opus 4.8max· Epoch AI Benchmarking Hub data57.5%
49GPT-5.6 Solhigh· Epoch AI Benchmarking Hub data56.9%
50Muse Wonder 1.0· Epoch AI Benchmarking Hub data56.8%

Showing 1–50 of 205 results.

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