OpenCompass Reasoning - Academic: leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 (High) | 56.7 |
| 2 | GPT-5.6 Sol (High) | 55.8 |
| 3 | GPT-5.5 (High) | 55.2 |
| 4 | Qwen 3.8 Max | 52.3 |
| 5 | Kimi K3 (High) | 51.7 |
| 6 | GLM-5.3 | 49.4 |
| 7 | DeepSeek V4 Flash | 49.1 |
| 8 | Claude Opus 4.8 (High) | 47.7 |
| 9 | Gemini 3.7 Flash | 47.4 |
| 10 | Grok 4.6 (High) | 44.8 |
| 11 | DeepSeek V4 Pro | 41.3 |
| 12 | MiniMax-M3 | 38.1 |
| 13 | Hy3-preview (High) | 36.9 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-reasoning-academic · How It Works · Data refreshed daily, snapshot 2026-09-05.