OpenCompass Knowledge - Humanities - Chinese (CompassBench 2411): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 34 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-11-20) | 68.2 |
| 2 | Claude 3.5 Sonnet (20241022) | 65.9 |
| 3 | Step 2 16K | 65.1 |
| 4 | GPT-4o (2024-08-06) | 62.8 |
| 5 | Llama 3.1 405B Instruct FP8 | 62 |
| 6 | Yi Lightning | 62 |
| 7 | Mistral Large 2 (Nov) Instruct (2411) | 59.7 |
| 8 | Llama 3.1 70B Instruct | 58.9 |
| 9 | Qwen 2.5 72B Instruct | 58.1 |
| 10 | GLM-4 Plus | 57.4 |
| 11 | DeepSeek V2.5 | 55.8 |
| 12 | TeleChat2 | 55.8 |
| 13 | 360gpt2-pro | 53.5 |
| 14 | O1 Mini (2024-09-12) | 49.6 |
| 15 | GLM-4 9B Chat | 45.7 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-knowledge-humanities-chinese-compassbench-2411 · How It Works · Data refreshed daily, snapshot 2026-09-19.