OpenCompass LLM - Reasoning (CompassBench 2404): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 31 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 Turbo (Preview) | 48.2 |
| 2 | OrionStar-Yi-34B-Chat | 44.3 |
| 3 | Yi 34B (Chat) | 37.6 |
| 4 | Qwen-72B-Chat | 31.4 |
| 5 | Qwen-14B-Chat | 29.1 |
| 6 | Baichuan2-13B-Chat | 23.9 |
| 7 | Qwen-7B Chat | 23.6 |
| 8 | Baichuan2-7B-Chat | 21.4 |
| 9 | Llama 2 13B Chat | 19.7 |
| 10 | WizardLM-70B-V1.0 | 18.5 |
| 11 | Yi 6B (Chat) | 17.9 |
| 12 | Mistral 7B Instruct (v0.2) | 17.8 |
| 13 | Llama 2 70B Chat | 17.3 |
| 14 | deepseek-llm-7B-chat | 16.2 |
| 15 | WizardLM-13B-V1.2 | 16 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-reasoning-compassbench-2404 · How It Works · Data refreshed daily, snapshot 2026-09-19.