SuperCLUE-Writing - Overall: 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, overall.
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) | 87.97 | #49 (Claude Opus 4.7) |
| 2 | Ernie 5.1 | 87.57 | #202 |
| 3 | Gemini 3.1 Pro (Preview) | 86.71 | #58 |
| 4 | Kimi K2.6 (Thinking) | 86.65 | #104 (Kimi K2.6) |
| 5 | Doubao-Seed-2.0-Pro-260215 | 86.52 | #77 |
| 6 | Qwen 3.6 Max (Preview) (Thinking) | 86.47 | |
| 7 | Grok 4.20 0309 (Reasoning) | 86.23 | #112 (Grok 4.20 0309) |
| 8 | GLM-5.1 | 85.71 | #97 |
| 9 | GPT-5.5 (xHigh) | 85.23 | #31 (GPT-5.5) |
| 10 | DeepSeek V4 Pro (Max) | 80.89 | #102 (DeepSeek V4 Pro) |
| 11 | DeepSeek V4 Flash (Max) | 76.61 | #137 (DeepSeek V4 Flash) |
| 12 | Hy3-preview (High) | 75.28 | #157 (Hy3-preview) |
| 13 | MiniMax-M2.7 | 56.47 | #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-overall · How It Works · Data refreshed daily, snapshot 2026-10-20.