OpenCompass LLM - Knowledge - Chinese (CompassBench 2409): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 30 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-08-06) | 81 |
| 2 | Llama 3.1 405B Instruct FP8 | 78.8 |
| 3 | Qwen 2.5 72B Instruct | 78.4 |
| 4 | Claude 3.5 Sonnet (20240620) | 77.9 |
| 5 | GPT-4o (2024-05-13) | 76.5 |
| 6 | GLM-4 Plus | 75.6 |
| 7 | Mistral Large 2 (Jul) | 75 |
| 8 | Step 2 16K | 73.3 |
| 9 | DeepSeek V2.5 | 73.3 |
| 10 | Yi Large | 69.6 |
| 11 | Llama 3.1 70B Instruct | 68.9 |
| 12 | GPT-4o Mini (2024-07-18) | 67.4 |
| 13 | Gemini 1.5 Pro | 65.1 |
| 14 | Gemma 2 27B (IT) | 63.4 |
| 15 | GLM-4 9B Chat | 63.1 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-knowledge-chinese-compassbench-2409 · How It Works · Data refreshed daily, snapshot 2026-09-19.