OpenCompass LLM - Reasoning — leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (High) | 64.4 |
| 2 | Claude Opus 4.7 (High) | 63.5 |
| 3 | Kimi K2.6 | 62.2 |
| 4 | Claude Sonnet 4.6 (High) | 60.6 |
| 5 | DeepSeek V4 Pro | 60 |
| 6 | Gemini 3.1 Pro (Preview) | 59.7 |
| 7 | Qwen 3.6 Max Preview | 59.2 |
| 8 | Hy3-preview (High) | 58.5 |
| 9 | DeepSeek V4 Flash | 57.2 |
| 10 | GPT-5.4 Mini (High) | 55.9 |
| 11 | Step 3.5 Flash | 55.6 |
| 12 | Gemma 4 31B (IT) | 54.6 |
| 13 | Qwen 3.5 397B A17B | 54.5 |
| 14 | GLM-5.1 | 54.3 |
| 15 | Qwen 3.6 27B | 52.7 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.