SuperCLUE General (March 2025) - Code Generation: leaderboard
SuperCLUE general leaderboard, March 2025 edition (2025年3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. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O3 Mini (High) | 88.78 | #282 (O3 Mini) |
| 2 | DeepSeek R1 | 86.94 | #262 |
| 3 | Claude 3.7 Sonnet | 86.73 | #259 |
| 4 | QwQ-32B | 81.84 | #422 |
| 5 | GPT-4.5 (Preview) | 79.18 | #260 |
| 6 | Gemini 2.0 Pro (Preview 02-05) | 77.76 | #318 |
| 7 | Doubao-1.5-pro-32k-250115 | 76.94 | #320 |
| 8 | DeepSeek R1 Distill Qwen 32B | 73.43 | #662 |
| 9 | DeepSeek V3 | 68.78 | #329 |
| 10 | Gemini 2.0 Flash (01-21) (Thinking) | 68.16 | #333 (Gemini 2.0 Flash (01-21)) |
| 11 | GPT-4o Mini | 63.06 | #598 |
| 12 | Llama 3.3 70B Instruct | 62.86 | #541 |
| 13 | Qwen 2.5 72B Instruct | 62.86 | #469 |
| 14 | Step 2 16K | 62.45 | #442 |
| 15 | GLM-4 Plus | 61.84 | #398 |
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-2025-code-generation · How It Works · Data refreshed daily, snapshot 2026-11-05.