OpenCompass Reasoning - Academic — leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (High) | 52 |
| 2 | Claude Opus 4.7 (High) | 50.9 |
| 3 | Kimi K2.6 | 48.8 |
| 4 | Claude Sonnet 4.6 (High) | 45.6 |
| 5 | DeepSeek V4 Pro | 43.9 |
| 6 | Gemini 3.1 Pro (Preview) | 43.6 |
| 7 | Hy3-preview (High) | 43.6 |
| 8 | Qwen 3.6 Max Preview | 43.3 |
| 9 | GPT-5.4 Mini (High) | 41.6 |
| 10 | DeepSeek V4 Flash | 39 |
| 11 | GLM-5.1 | 38.7 |
| 12 | Step 3.5 Flash | 38.7 |
| 13 | Gemma 4 31B (IT) | 38.1 |
| 14 | Qwen 3.5 397B A17B | 36.6 |
| 15 | Qwen 3.6 27B | 36 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-reasoning-academic · How the rankings work · Data refreshed daily, snapshot 2026-07-22.