OpenCompass Reasoning - Common: leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 (High) | 80.6 |
| 2 | Claude Opus 5 (High) | 80.1 |
| 3 | GPT-5.5 (High) | 78.6 |
| 4 | Qwen 3.8 Max | 78.1 |
| 5 | GPT-5.6 Sol (High) | 77.8 |
| 6 | Gemini 3.7 Flash | 76.8 |
| 7 | Kimi K3 (High) | 76 |
| 8 | Grok 4.6 (High) | 75.3 |
| 9 | GLM-5.3 | 74.5 |
| 10 | DeepSeek V4 Flash | 73 |
| 11 | Hy3-preview (High) | 72.2 |
| 12 | MiniMax-M3 | 69.9 |
| 13 | DeepSeek V4 Pro | 69.6 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-reasoning-common · How It Works · Data refreshed daily, snapshot 2026-09-05.