SuperCLUE General (July 2025) - Code Generation: leaderboard
Metric: Score. Source: www.superclueai.com. 47 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 (High) | 87.92 |
| 2 | O4 Mini (High) | 86.14 |
| 3 | Doubao-Seed-1.6-thinking-250715 | 84.36 |
| 4 | O3 (High) | 83.76 |
| 5 | DeepSeek V3.1 (Thinking) | 83.56 |
| 6 | Gemini 2.5 Pro | 82.38 |
| 7 | Grok 4 | 82.18 |
| 8 | Qwen 3 235B A22B 2507 (Thinking) | 81.78 |
| 9 | Claude Opus 4 (Thinking) | 80.4 |
| 10 | SenseNova V6 Reasoner | 80.2 |
| 11 | Kimi K2 (0711) | 80 |
| 12 | GLM-4.5 | 79.01 |
| 13 | Qwen 3 235B A22B 2507 Instruct | 78.42 |
| 14 | Qwen 3 32B (Thinking) | 76.24 |
| 15 | MiniMax-M1 | 75.84 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-july-2025-code-generation · How It Works · Data refreshed daily, snapshot 2026-09-19.