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
151Qwen3.5 Flash· Epoch AI Benchmarking Hub data29.1%
152DeepSeek V3.2 Expthinking· Epoch AI Benchmarking Hub data29.1%
153Claude Sonnet 4· Epoch AI Benchmarking Hub data29%
154DeepSeek V3.2· Epoch AI Benchmarking Hub data28.8%
155DeepSeek V3.1 Terminus· Epoch AI Benchmarking Hub data28.6%
156Qwen3 Max· Epoch AI Benchmarking Hub data28.3%
157Gemini 2.5 Flash· Epoch AI Benchmarking Hub data27.5%
158o4 Minihigh· Epoch AI Benchmarking Hub data26.5%
159Mistral Medium2604· Epoch AI Benchmarking Hub data26.1%
160GPT 4.1· Epoch AI Benchmarking Hub data25.6%
161Qwen 3 235B A22B· Epoch AI Benchmarking Hub data25%
162Qwen3.5 9B· Epoch AI Benchmarking Hub data24.5%
163DeepSeek V3.1thinking· Epoch AI Benchmarking Hub data24.3%
164Qwen Plus· Epoch AI Benchmarking Hub data24%
165Qwen3 235B A22B Instruct 2507· Epoch AI Benchmarking Hub data23.5%
166Qwen3 30B A3B Instruct· Epoch AI Benchmarking Hub data22.4%
167o1high· Epoch AI Benchmarking Hub data22.3%
168GPT OSS 120Bhigh· Epoch AI Benchmarking Hub data22.1%
169GPT-4.1 mini· Epoch AI Benchmarking Hub data21.1%
170Mistral Small2603· Epoch AI Benchmarking Hub data20.6%
171Qwen3 30B A3B2507, thinking· Epoch AI Benchmarking Hub data19.5%
172Mistral Medium 3.1· Epoch AI Benchmarking Hub data19.1%
173o3 Minihigh· Epoch AI Benchmarking Hub data19%
174Qwen3 14B· Epoch AI Benchmarking Hub data18.2%
175Gemini 2.5 Flash-Litethinking· Epoch AI Benchmarking Hub data18.1%
176Llama 3.3 70B Instruct· Epoch AI Benchmarking Hub data17.5%
177Qwen3 32B· Epoch AI Benchmarking Hub data17.3%
178GPT 4· Epoch AI Benchmarking Hub data17.1%
179Claude 3 Opus· Epoch AI Benchmarking Hub data17%
180Mistral Large 3· Epoch AI Benchmarking Hub data16.7%
181GPT 4o· Epoch AI Benchmarking Hub data16.6%
182Llama 4 Maverick· Epoch AI Benchmarking Hub data15.9%
183Qwen3 30B A3B· Epoch AI Benchmarking Hub data15.8%
184DeepSeek V3· Epoch AI Benchmarking Hub data15.5%
185DeepSeek Chat· Epoch AI Benchmarking Hub data15.2%
186Llama 3.1 70B Instruct· Epoch AI Benchmarking Hub data14.9%
187GPT OSS 20bhigh· Epoch AI Benchmarking Hub data14.5%
188Qwen2.5 72B Instruct· Epoch AI Benchmarking Hub data13.4%
189Gemma 3 27B IT· Epoch AI Benchmarking Hub data12.3%
190Llama 4 Scout· Epoch AI Benchmarking Hub data12%
191GPT-4o mini· Epoch AI Benchmarking Hub data10.4%
192C4AI Command A 03 2025· Epoch AI Benchmarking Hub data10.3%
193GPT-4 Turbo· Epoch AI Benchmarking Hub data9.8%
194GPT-3.5 Turbo· Epoch AI Benchmarking Hub data9.7%
195C4AI Command R 08 2024· Epoch AI Benchmarking Hub data9.2%
196Claude 3 Haiku· Epoch AI Benchmarking Hub data8.8%
197Qwen3 8B· Epoch AI Benchmarking Hub data8.8%
198GPT-5 nanohigh· Epoch AI Benchmarking Hub data7.9%
199gemma2-27b· Epoch AI Benchmarking Hub data7.1%
200Qwen2.5 7B Instruct· Epoch AI Benchmarking Hub data6.4%

Showing 151–200 of 205 results.

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