SuperCLUE General (May 2026) - Code Generation: leaderboard
Metric: Score. Source: www.superclueai.com. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 (High) | 83.58 |
| 2 | Gemini 3.1 Pro (Preview) (High) | 81.47 |
| 3 | Claude Opus 4.7 (High) | 79.01 |
| 4 | Kimi K2.6 (Thinking) | 75.79 |
| 5 | DeepSeek V4 Pro (Max) | 74.95 |
| 6 | GPT-5.5 (High) | 72.88 |
| 7 | GLM-5.1 | 70.8 |
| 8 | Gemini 3.5 Flash (High) | 70.66 |
| 9 | MiMo-V2.5-Pro | 67.52 |
| 10 | DeepSeek V4 Flash (Max) | 66.75 |
| 11 | Grok 4.3 | 66.73 |
| 12 | Qwen 3.6 Max (Preview) (Thinking) | 66.21 |
| 13 | MiniMax-M3 | 65.84 |
| 14 | Gemma 4 31B | 65.76 |
| 15 | Step 3.7 Flash | 65.33 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-may-2026-code-generation · How It Works · Data refreshed daily, snapshot 2026-09-19.