OpenCompass Reasoning - Inductive - Chinese (CompassBench 2404): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 31 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 Turbo (Preview) | 39.4 |
| 2 | OrionStar-Yi-34B-Chat | 34.1 |
| 3 | Qwen-72B-Chat | 31.2 |
| 4 | Qwen-7B Chat | 30.2 |
| 5 | Yi 34B (Chat) | 29.1 |
| 6 | Qwen-14B-Chat | 27.5 |
| 7 | WizardLM-70B-V1.0 | 27.4 |
| 8 | Baichuan2-7B-Chat | 26.9 |
| 9 | Baichuan2-13B-Chat | 26.3 |
| 10 | deepseek-llm-7B-chat | 24.7 |
| 11 | Yi 6B (Chat) | 24.6 |
| 12 | WizardLM-13B-V1.2 | 21.9 |
| 13 | Llama 2 13B Chat | 11.5 |
| 14 | Mistral 7B Instruct (v0.2) | 5.5 |
| 15 | Llama 2 7B Chat | 3.9 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-reasoning-inductive-chinese-compassbench-2404 · How It Works · Data refreshed daily, snapshot 2026-09-19.