SuperCLUE General (March 2025) - Code Generation: leaderboard
Metric: Score. Source: www.superclueai.com. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 Mini (High) | 88.78 |
| 2 | DeepSeek R1 | 86.94 |
| 3 | Claude 3.7 Sonnet | 86.73 |
| 4 | QwQ-32B | 81.84 |
| 5 | GPT-4.5 (Preview) | 79.18 |
| 6 | Gemini 2.0 Pro (Preview 02-05) | 77.76 |
| 7 | Doubao-1.5-pro-32k-250115 | 76.94 |
| 8 | hunyuan-turbos-20250226 | 74.49 |
| 9 | DeepSeek R1 Distill Qwen 32B | 73.43 |
| 10 | DeepSeek V3 | 68.78 |
| 11 | Gemini 2.0 Flash (01-21) (Thinking) | 68.16 |
| 12 | GPT-4o Mini | 63.06 |
| 13 | Llama 3.3 70B Instruct | 62.86 |
| 14 | Qwen 2.5 72B Instruct | 62.86 |
| 15 | Step 2 16K | 62.45 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-march-2025-code-generation · How It Works · Data refreshed daily, snapshot 2026-09-19.