OpenCompass LLM - Math - Chinese (CompassBench 2404): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 51 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-05-13) | 61.1 |
| 2 | GPT-4 Turbo | 56.4 |
| 3 | Claude 3 Opus | 55.8 |
| 4 | GPT-4 Turbo (Preview) | 53.7 |
| 5 | Qwen 1.5 110B Chat | 52.9 |
| 6 | DeepSeek V2 Chat | 51.9 |
| 7 | Llama 3 70B Instruct | 51.6 |
| 8 | GLM-4 | 51.2 |
| 9 | Moonshot v1 8K | 50 |
| 10 | Qwen 1.5 72B Chat | 49.5 |
| 11 | Qwen-72B-Chat | 47.5 |
| 12 | Mistral Large | 45.4 |
| 13 | Qwen 1.5 14B Chat | 41.6 |
| 14 | Qwen-14B-Chat | 38.9 |
| 15 | internlm2-chat-20B | 38.8 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-math-chinese-compassbench-2404 · How It Works · Data refreshed daily, snapshot 2026-09-19.