OpenCompass Math - College - Chinese (CompassBench 2407): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Large 2 (Jul) | 72 |
| 2 | Mistral Large | 69 |
| 3 | GPT-4o (2024-05-13) | 65.5 |
| 4 | Qwen 2 72B Instruct | 65 |
| 5 | Claude 3.5 Sonnet (20240620) | 64 |
| 6 | DeepSeek V2 Chat (0628) | 64 |
| 7 | GPT-4o Mini (2024-07-18) | 59 |
| 8 | GLM-4 (0520) | 59 |
| 9 | Yi Large | 55 |
| 10 | Qwen 1.5 110B Chat | 54.5 |
| 11 | GLM-4 9B Chat | 52.5 |
| 12 | Gemma 2 27B (IT) | 49.5 |
| 13 | Qwen 2 7B Instruct | 48.5 |
| 14 | Moonshot v1 8K | 48 |
| 15 | Llama 3.1 70B Instruct | 45 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-math-college-chinese-compassbench-2407 · How It Works · Data refreshed daily, snapshot 2026-09-19.