OpenCompass LLM - Math - Chinese (CompassBench 2409): leaderboard

Metric: Score (%). Source: rank.opencompass.org.cn. 30 models tracked.

Top models

#ModelScore
1Qwen 2.5 72B Instruct79.9
2Claude 3.5 Sonnet (20240620)75.5
3Mistral Large 2 (Jul)74.9
4GPT-4o (2024-05-13)74.8
5GPT-4o (2024-08-06)74.2
6GLM-4 Plus73
7DeepSeek V2.572.3
8Qwen 2.5 7B Instruct71.3
9Llama 3.1 405B Instruct FP869.8
10Gemini 1.5 Pro68.9
11GPT-4o Mini (2024-07-18)67.2
12Step 2 16K66.2
13Mistral-Small-Instruct-240962.4
14Gemma 2 27B (IT)60.5
15Yi Large60.2

Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-math-chinese-compassbench-2409 · How It Works · Data refreshed daily, snapshot 2026-09-19.