SuperCLUE General (March 2026) - Code Generation: leaderboard
SuperCLUE general leaderboard, March 2026 edition (2026年3月): code generation (代码生成) score from the 总排行榜 sheet. SuperCLUE's periodic Chinese-language general evaluation uses a new question set each edition, so editions are separate boards. Score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around July 2027. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 (Max) | 71.15 | #67 (Claude Opus 4.6) |
| 2 | Gemini 3.1 Pro (Preview) (High) | 69.78 | #64 (Gemini 3.1 Pro (Preview)) |
| 3 | Kimi K2.5 (Thinking) | 65.5 | #152 (Kimi K2.5) |
| 4 | Gemini 3 Flash (Preview) (High) | 63.94 | #90 (Gemini 3 Flash (Preview)) |
| 5 | Doubao-Seed-2-0-Pro-260215 (High) | 63.93 | |
| 6 | DeepSeek V4 Pro (Max) | 63.24 | #112 (DeepSeek V4 Pro) |
| 7 | DeepSeek V4 Flash (Max) | 61.43 | #155 (DeepSeek V4 Flash) |
| 8 | DeepSeek V3.2 (Thinking) | 60.43 | #210 (DeepSeek V3.2) |
| 9 | MiMo-V2-Pro | 59.61 | #177 |
| 10 | MiniMax-M2.7 | 58.74 | #270 |
| 11 | GLM-5 | 58.32 | #149 |
| 12 | Tencent HY 2.0 Think | 57.58 | #206 |
| 13 | MiniMax-M2.5 | 55.33 | #316 |
| 14 | Grok 4.20 Beta (0309) (Reasoning) | 55.01 | #198 (Grok 4.20 Beta (0309)) |
| 15 | MiMo-V2-Flash | 54.46 | #378 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-march-2026-code-generation · How It Works · Data refreshed daily, snapshot 2026-11-05.