OpenCompass Language - Creation — leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (High) | 82.5 |
| 2 | Qwen 3.6 Max Preview | 77.9 |
| 3 | Hy3-preview (High) | 75.4 |
| 4 | Gemini 3.1 Pro (Preview) | 73.8 |
| 5 | Kimi K2.6 | 73.8 |
| 6 | GPT-5.4 Mini (High) | 72.1 |
| 7 | Claude Sonnet 4.6 (High) | 70.8 |
| 8 | DeepSeek V4 Pro | 70 |
| 9 | GLM-5.1 | 69.2 |
| 10 | Claude Opus 4.7 (High) | 67.1 |
| 11 | MiniMax-M2.7 | 66.7 |
| 12 | Qwen 3.5 397B A17B | 66.2 |
| 13 | Qwen 3.6 27B | 65.8 |
| 14 | DeepSeek V4 Flash | 65 |
| 15 | Step 3.5 Flash | 63.8 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-language-creation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.