OpenCompass Reasoning - Common — leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (High) | 76.8 |
| 2 | DeepSeek V4 Pro | 76 |
| 3 | Claude Opus 4.7 (High) | 76 |
| 4 | Gemini 3.1 Pro (Preview) | 75.8 |
| 5 | Kimi K2.6 | 75.5 |
| 6 | DeepSeek V4 Flash | 75.5 |
| 7 | Claude Sonnet 4.6 (High) | 75.5 |
| 8 | Qwen 3.6 Max Preview | 75 |
| 9 | Hy3-preview (High) | 73.5 |
| 10 | Qwen 3.5 397B A17B | 72.5 |
| 11 | Step 3.5 Flash | 72.5 |
| 12 | Gemma 4 31B (IT) | 71.2 |
| 13 | GPT-5.4 Mini (High) | 70.2 |
| 14 | GLM-5.1 | 69.9 |
| 15 | Gemini 3.1 Flash Lite (Preview) | 69.6 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-reasoning-common · How the rankings work · Data refreshed daily, snapshot 2026-07-22.