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
51GPT-5.6 Solmedium· Epoch AI Benchmarking Hub data56.4%
52GPT-5.6 Sollow· Epoch AI Benchmarking Hub data55.9%
53Claude Opus 4.6max· Epoch AI Benchmarking Hub data55.8%
54GLM 5.3· Epoch AI Benchmarking Hub data55.5%
55GPT-5.6 Terramax· Epoch AI Benchmarking Hub data55%
56GPT 5.5xhigh· Epoch AI Benchmarking Hub data54.3%
57GPT-5.5 Proxhigh· Epoch AI Benchmarking Hub data53.9%
58Muse Spark 1.3· Epoch AI Benchmarking Hub data53.9%
59Gemini 3.1 Pro Previewhigh· Epoch AI Benchmarking Hub data53.8%
60Gemini 3.8 Flashmedium· Epoch AI Benchmarking Hub data52.9%
61Gemini 3.1 Pro Previewmedium· Epoch AI Benchmarking Hub data52.8%
62GPT-5.6 Solnone· Epoch AI Benchmarking Hub data52.8%
63Kimi K3max· Epoch AI Benchmarking Hub data52.7%
64GPT-5.6 Terraxhigh· Epoch AI Benchmarking Hub data52.2%
65Claude Opus 4.7max· Epoch AI Benchmarking Hub data52.2%
66GPT 5.4xhigh· Epoch AI Benchmarking Hub data52%
67Gemini 3.8 Flash· Epoch AI Benchmarking Hub data51.6%
68GPT-5.6 Terrahigh· Epoch AI Benchmarking Hub data51.4%
69Gemini 3.1 Pro Previewlow· Epoch AI Benchmarking Hub data51.2%
70Gemini 3.8 Flashlow· Epoch AI Benchmarking Hub data51.2%
71Claude Haiku 5.5max· Epoch AI Benchmarking Hub data51.1%
72Gemini 3.7 Flashhigh· Epoch AI Benchmarking Hub data50.4%
73Claude Sonnet 5high· Epoch AI Benchmarking Hub data50%
74Muse Spark 1.1high· Epoch AI Benchmarking Hub data49.9%
75Claude Sonnet 5medium· Epoch AI Benchmarking Hub data49.7%
76Claude Sonnet 5low· Epoch AI Benchmarking Hub data49.7%
77GPT-5.6 Terramedium· Epoch AI Benchmarking Hub data49.6%
78Grok 4.7xhigh· Epoch AI Benchmarking Hub data49.4%
79Claude Sonnet 5max· Epoch AI Benchmarking Hub data49.3%
80GPT-5.6 Terralow· Epoch AI Benchmarking Hub data49.3%
81Gemini 3.7 Flashmedium· Epoch AI Benchmarking Hub data49.2%
82Claude Sonnet 5xhigh· Epoch AI Benchmarking Hub data48.8%
83GPT-5.6 Lunamax· Epoch AI Benchmarking Hub data48.5%
84GPT-5.6 Lunaxhigh· Epoch AI Benchmarking Hub data48.5%
85Grok 4.6xhigh· Epoch AI Benchmarking Hub data48.5%
86Muse Spark 1.2xhigh· Epoch AI Benchmarking Hub data48.4%
87Claude Haiku 5.5xhigh· Epoch AI Benchmarking Hub data48%
88GPT-5.6 Lunahigh· Epoch AI Benchmarking Hub data47.4%
89Gemini 3.5 Flashhigh· Epoch AI Benchmarking Hub data47.2%
90Gemini 3.7 Flashlow· Epoch AI Benchmarking Hub data47.1%
91DeepSeek V4.1 Flash· Epoch AI Benchmarking Hub data47%
92Claude Sonnet 4.6max· Epoch AI Benchmarking Hub data46.5%
93GPT-5.6 Terranone· Epoch AI Benchmarking Hub data46.5%
94Qwen3.8 Maxxhigh· Epoch AI Benchmarking Hub data46.2%
95GLM 5.2max· Epoch AI Benchmarking Hub data45.8%
96Claude Haiku 5.5medium· Epoch AI Benchmarking Hub data45.6%
97DeepSeek V4 Pro 0813· Epoch AI Benchmarking Hub data45.5%
98Claude Haiku 5.5high· Epoch AI Benchmarking Hub data45.2%
99Grok 4.5high· Epoch AI Benchmarking Hub data45.2%
100Gemini 3.6 Flashhigh· Epoch AI Benchmarking Hub data44.9%

Showing 51–100 of 205 results.

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