SuperCLUE-Writing - Content Quality: leaderboard
SuperCLUE is the Chinese-language evaluation programme run by CLUE; its specialised boards each cover one professional domain and are graded by the organisers rather than self-reported. This board covers Chinese writing judged on quality.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around September 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 (Max) | 90.77 | #49 (Claude Opus 4.7) |
| 2 | Ernie 5.1 | 89.59 | #202 |
| 3 | Qwen 3.6 Max (Preview) (Thinking) | 86.67 | |
| 4 | Doubao-Seed-2.0-Pro-260215 | 86.3 | #77 |
| 5 | GLM-5.1 | 86.08 | #97 |
| 6 | Grok 4.20 0309 (Reasoning) | 86.06 | #112 (Grok 4.20 0309) |
| 7 | Gemini 3.1 Pro (Preview) | 85.04 | #58 |
| 8 | Kimi K2.6 (Thinking) | 84.11 | #104 (Kimi K2.6) |
| 9 | GPT-5.5 (xHigh) | 81.32 | #31 (GPT-5.5) |
| 10 | DeepSeek V4 Pro (Max) | 73.79 | #102 (DeepSeek V4 Pro) |
| 11 | DeepSeek V4 Flash (Max) | 66.4 | #137 (DeepSeek V4 Flash) |
| 12 | Hy3-preview (High) | 60.63 | #157 (Hy3-preview) |
| 13 | MiniMax-M2.7 | 50.47 | #258 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-writing-content-quality · How It Works · Data refreshed daily, snapshot 2026-10-20.