SuperCLUE General (May 2025) - Code Generation: leaderboard
SuperCLUE general leaderboard, May 2025 edition (2025年5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. 40 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O4 Mini (High) | 91.52 | #185 (O4 Mini) |
| 2 | Gemini 2.5 Pro (Preview 05-06) | 91.32 | #156 |
| 3 | Qwen 3 235B A22B (Thinking) | 90.53 | #323 (Qwen 3 235B A22B) |
| 4 | O3 | 88.76 | #132 |
| 5 | Doubao-1.5-thinking-pro-250415 | 87.97 | #226 |
| 6 | Qwen 3 32B (Thinking) | 87.18 | #449 (Qwen 3 32B) |
| 7 | 360Zhinao2-O1.5 | 87.14 | #395 |
| 8 | Claude Opus 4 (Thinking) | 86.98 | #170 (Claude Opus 4) |
| 9 | Gemini 2.5 Flash (Preview 05-20) | 86.79 | #229 |
| 10 | DeepSeek R1 | 86.59 | #262 |
| 11 | Gemini 2.5 Flash (Preview 04-17) | 86.59 | #246 |
| 12 | SenseNova V6 Reasoner | 86.19 | #317 |
| 13 | DeepSeek V3 (0324) | 84.81 | #349 |
| 14 | Qwen 3 30B A3B (Thinking) | 83.04 | #496 (Qwen 3 30B A3B) |
| 15 | ERNIE-X1-Turbo-32K | 82.25 | #288 |
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-may-2025-code-generation · How It Works · Data refreshed daily, snapshot 2026-11-05.