OpenCompass Knowledge - Humanities - English (CompassBench 2407): leaderboard

Metric: Score (%). Source: rank.opencompass.org.cn. 36 models tracked.

Top models

#ModelScore
1GPT-4o (2024-05-13)88
2Claude 3.5 Sonnet (20240620)86.4
3Qwen 2 72B Instruct85.6
4Mistral Large 2 (Jul)85.6
5Mistral Large83.2
6Llama 3.1 70B Instruct81.6
7Mixtral 8x22B Instruct (v0.1)77.6
8GPT-4o Mini (2024-07-18)76.8
9Qwen 1.5 110B Chat75.2
10GLM-4 (0520)73.6
11Yi Large72.8
12DBRX72
13DeepSeek V2 Chat (0628)72
14Llama 3.1 8B Instruct66.4
15Yi 1.5 34B Chat65.6

Interactive version: theaggregate.ai/benchmark?slug=opencompass-knowledge-humanities-english-compassbench-2407 · How It Works · Data refreshed daily, snapshot 2026-09-19.