SuperCLUE General (November 2026) - Precise Instruction Following: leaderboard
SuperCLUE general leaderboard, November 2026 edition: precise instruction-following dimension (精确指令遵循) of the Chinese-language general evaluation. Native score, higher is better; kept separate from other dimensions and monthly editions. Source: https://www.superclueai.com/generalpage
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around September 2027. 19 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 68.97 | #11 |
| 2 | GPT-6.1 Sol | 68.97 | #10 |
| 3 | Kimi K3.1 Pro | 44.83 | #28 |
| 4 | DeepSeek V4.1 Flash (1017) | 43.1 | #38 |
| 5 | Hy4 preview | 31.03 | #66 |
| 6 | Grok 4.7 | 27.59 | #43 |
| 7 | GLM-5.3 Flash | 20.69 | #119 |
| 8 | Qwen 3.8 Max (0902) | 20.69 | #49 |
| 9 | GLM-5.3 | 17.24 | #62 |
| 10 | MiMo-V2.6-Pro | 15.52 | #68 |
| 11 | Qwen 3.8 Flash | 12.07 | #109 |
| 12 | MiniMax-M3 | 10.34 | #265 |
| 13 | Step 5 Preview | 8.62 | #105 |
| 14 | MiMo-V2.6-Flash | 6.9 | #150 |
| 15 | MiniMax-M3.1-Flash | 5.17 | #104 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-november-2026-precise-instruction-following · How It Works · Data refreshed daily, snapshot 2026-11-12.