OpenCompass Knowledge - Humanities - Chinese (CompassBench 2409): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 30 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-08-06) | 75 |
| 2 | Llama 3.1 405B Instruct FP8 | 72.3 |
| 3 | Claude 3.5 Sonnet (20240620) | 70.5 |
| 4 | Mistral Large 2 (Jul) | 70.5 |
| 5 | Step 2 16K | 69.6 |
| 6 | GPT-4o (2024-05-13) | 68.8 |
| 7 | DeepSeek V2.5 | 68.8 |
| 8 | Qwen 2.5 72B Instruct | 67.9 |
| 9 | GLM-4 Plus | 67.9 |
| 10 | Llama 3.1 70B Instruct | 65.2 |
| 11 | Gemini 1.5 Pro | 58 |
| 12 | Yi Large | 57.1 |
| 13 | GPT-4o Mini (2024-07-18) | 56.2 |
| 14 | Gemma 2 27B (IT) | 54.5 |
| 15 | GLM-4 9B Chat | 52.7 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-knowledge-humanities-chinese-compassbench-2409 · How It Works · Data refreshed daily, snapshot 2026-09-19.