SuperCLUE General (2025 Annual) - Code Generation: leaderboard
SuperCLUE general leaderboard, 2025 Annual edition (2025年度测评): 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 October 2027. 34 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 (High) | 59.91 | #67 (Claude Opus 4.6) |
| 2 | Gemini 3.1 Pro (Preview) (High) | 55.05 | #64 (Gemini 3.1 Pro (Preview)) |
| 3 | Kimi K2.5 (Thinking) | 53.33 | #152 (Kimi K2.5) |
| 4 | GLM-5 | 51.35 | #149 |
| 5 | Grok 4 | 49.51 | #189 |
| 6 | Doubao-Seed-2.0-Pro-260215 | 48.77 | #86 |
| 7 | Claude Opus 4.5 (Thinking) | 48.4 | #87 (Claude Opus 4.5) |
| 8 | Qwen 3 Max (2025-09-23) | 47.23 | #276 |
| 9 | Gemini 3 Pro (Preview) | 47.17 | #71 |
| 10 | Kimi K2 (Thinking) | 46 | #252 (Kimi K2) |
| 11 | ERNIE 5.0 | 45.63 | #243 |
| 12 | Qwen 3.5 397B A17B (Thinking) | 41.63 | #154 (Qwen 3.5 397B A17B) |
| 13 | Qwen 3 Max (Thinking) | 41.56 | #213 (Qwen 3 Max) |
| 14 | GLM-4.7 | 41.26 | #202 |
| 15 | MiniMax-M2.1 | 41.26 | #299 |
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-2025-annual-code-generation · How It Works · Data refreshed daily, snapshot 2026-11-05.