SuperCLUE General (September 2025) - Code Generation: leaderboard
SuperCLUE general leaderboard, September 2025 edition (2025年9月): code generation (代码生成) score (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: Estimated already saturated. 37 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 73.65 | #148 (Claude Sonnet 4.5) |
| 2 | GPT-5.1 (High) | 71.04 | #145 (GPT-5.1) |
| 3 | GPT-5 (High) | 70.85 | #105 (GPT-5) |
| 4 | Claude Opus 4.1 (Thinking) | 70.85 | #146 (Claude Opus 4.1) |
| 5 | Gemini 3 Pro (Preview) | 68.44 | #71 |
| 6 | Qwen 3 Max | 67.18 | #213 |
| 7 | GLM-4.5 | 66.41 | #283 |
| 8 | DeepSeek V3.2 Exp (Thinking) | 66.12 | #241 (DeepSeek V3.2 Exp) |
| 9 | GLM-4.6 | 65.25 | #265 |
| 10 | Grok 4 | 64.48 | #189 |
| 11 | O4 Mini (High) | 64.38 | #185 (O4 Mini) |
| 12 | Kimi K2 (Thinking) | 63.03 | #252 (Kimi K2) |
| 13 | O3 (High) | 62.16 | #132 (O3) |
| 14 | DeepSeek V3.1 Terminus (Thinking) | 61.68 | #224 (DeepSeek V3.1 Terminus) |
| 15 | Kimi K2 0905 | 60.42 | #292 |
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-september-2025-code-generation · How It Works · Data refreshed daily, snapshot 2026-11-05.