OpenCompass Language - Content Critique - English (CompassBench 2404): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 31 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 Turbo (Preview) | 50 |
| 2 | OrionStar-Yi-34B-Chat | 42 |
| 3 | Llama 2 70B Chat | 38 |
| 4 | Yi 34B (Chat) | 32 |
| 5 | Qwen-14B-Chat | 24 |
| 6 | Qwen-72B-Chat | 22 |
| 7 | Llama 2 13B Chat | 18 |
| 8 | WizardLM-13B-V1.2 | 16 |
| 9 | Baichuan2-13B-Chat | 16 |
| 10 | Llama 2 7B Chat | 10 |
| 11 | Mistral 7B Instruct (v0.2) | 8 |
| 12 | WizardLM-70B-V1.0 | 6 |
| 13 | Qwen-7B Chat | 4 |
| 14 | Yi 6B (Chat) | 2 |
| 15 | deepseek-llm-7B-chat | 2 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-language-content-critique-english-compassbench-2404 · How It Works · Data refreshed daily, snapshot 2026-09-19.