OpenCompass Knowledge - Humanities — leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.6 | 93.8 |
| 2 | DeepSeek V4 Pro | 92.9 |
| 3 | Gemini 3.1 Pro (Preview) | 92.5 |
| 4 | DeepSeek V4 Flash | 92.5 |
| 5 | Claude Opus 4.7 (High) | 92.1 |
| 6 | GPT-5.4 (High) | 91.7 |
| 7 | Gemma 4 31B (IT) | 90 |
| 8 | Gemini 3.1 Flash Lite (Preview) | 90 |
| 9 | GLM-5.1 | 90 |
| 10 | Qwen 3.5 397B A17B | 90 |
| 11 | GPT-5.4 Mini (High) | 89.6 |
| 12 | Hy3-preview (High) | 89.2 |
| 13 | Claude Sonnet 4.6 (High) | 87.9 |
| 14 | Qwen 3.6 Max Preview | 87.5 |
| 15 | Step 3.5 Flash | 84.6 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-knowledge-humanities · How the rankings work · Data refreshed daily, snapshot 2026-07-22.