OpenCompass Language - Dialogue - Chinese (CompassBench 2407): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-05-13) | 65.9 |
| 2 | Mistral Large 2 (Jul) | 58.2 |
| 3 | Mistral Large | 58.2 |
| 4 | Qwen 1.5 110B Chat | 55.8 |
| 5 | Yi 1.5 34B Chat | 54.8 |
| 6 | Yi-1.5-9B Chat | 53.9 |
| 7 | GPT-4o Mini (2024-07-18) | 52.9 |
| 8 | Qwen 2 72B Instruct | 52.6 |
| 9 | Qwen 2 7B Instruct | 51.7 |
| 10 | Yi-1.5-6B-Chat | 51.2 |
| 11 | GLM-4 9B Chat | 51 |
| 12 | Yi Large | 49 |
| 13 | GLM-4 (0520) | 48.3 |
| 14 | Moonshot v1 8K | 46.9 |
| 15 | internlm2-chat-20B | 46.9 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-language-dialogue-chinese-compassbench-2407 · How It Works · Data refreshed daily, snapshot 2026-09-19.