Skip to content

Benchmark

Dtbench CRI-rescaled score

Scores are percentages.

Models measured
170
Scores recorded
239
Sources
1
IQ weight
1.22

Score distribution

66.3%
Mean
74.2%
Median
27.6%
Std dev
20.9%
10th percentile
95.1%
90th percentile
2.8%
Min
2.8%98.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.22 for chat models, measured over 170 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
201Mistral Small2506· Epoch AI Benchmarking Hub data33.1%
202Qwen3 8B· Epoch AI Benchmarking Hub data32.9%
203Llama 3.3 70B Instruct· Epoch AI Benchmarking Hub data32.5%
204gemini-1.5-pro-002· Epoch AI Benchmarking Hub data31.6%
205Mistral Small2503· Epoch AI Benchmarking Hub data31.1%
206Llama 4 Scout· Epoch AI Benchmarking Hub data29.8%
207Claude Haiku 3.5· Epoch AI Benchmarking Hub data27.8%
208gemini-1.5-pro-001· Epoch AI Benchmarking Hub data27.5%
209Mistral Large2402· Epoch AI Benchmarking Hub data26.5%
210Mixtral 8x22B Instruct v0.1· Epoch AI Benchmarking Hub data25.2%
211GPT-4o mini· Epoch AI Benchmarking Hub data24%
212Llama 3 70B Instruct· Epoch AI Benchmarking Hub data23.6%
213gemini-1.5-flash-002· Epoch AI Benchmarking Hub data23%
214Claude 3 Sonnet· Epoch AI Benchmarking Hub data22.7%
215Mistral Small· Epoch AI Benchmarking Hub data21.6%
216Gemini 2.0 Flash Lite· Epoch AI Benchmarking Hub data20.9%
217Gemma 3 27B IT· Epoch AI Benchmarking Hub data20.9%
218GPT-4.1 nano· Epoch AI Benchmarking Hub data20.9%
219Claude 2· Epoch AI Benchmarking Hub data19.7%
220Ministral 3B· Epoch AI Benchmarking Hub data19.6%
221gemini-1.5-flash-001· Epoch AI Benchmarking Hub data19%
222Claude 2.1· Epoch AI Benchmarking Hub data18.2%
223Gemma 3 4B IT· Epoch AI Benchmarking Hub data18.2%
224Llama 3.1 8B Instruct· Epoch AI Benchmarking Hub data18.2%
225Claude 3 Haiku· Epoch AI Benchmarking Hub data16.9%
226gemini-1.5-flash-8b-001· Epoch AI Benchmarking Hub data16.7%
227open-mixtral-8x7b· Epoch AI Benchmarking Hub data16%
228Gemma 3 12B IT· Epoch AI Benchmarking Hub data14.7%
229Mistral Nemo· Epoch AI Benchmarking Hub data14.3%
230GPT-3.5 Turbo· Epoch AI Benchmarking Hub data14.2%
231gemma2-27b· Epoch AI Benchmarking Hub data13.3%
232Qwen2.5 7B Instruct· Epoch AI Benchmarking Hub data12.9%
233C4AI Command R 08 2024· Epoch AI Benchmarking Hub data10.7%
234Claude Instant 1.2· Epoch AI Benchmarking Hub data9.6%
235Ministral 8B· Epoch AI Benchmarking Hub data9.5%
236Llama 3 8B Instruct· Epoch AI Benchmarking Hub data6.6%
237open-mistral-7b· Epoch AI Benchmarking Hub data4.2%
238Llama 2 13B Chat· Epoch AI Benchmarking Hub data3.7%
239Llama 2 70B Chat· Epoch AI Benchmarking Hub data2.8%

Showing 201–239 of 239 results.

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