SuperCLUE General (May 2026) - Math Reasoning: leaderboard
Metric: Score. Source: www.superclueai.com. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Flash (Max) | 82.69 |
| 2 | Gemini 3.5 Flash (High) | 82.46 |
| 3 | Gemini 3.1 Pro (Preview) (High) | 82.46 |
| 4 | GPT-5.5 (High) | 82.46 |
| 5 | Claude Opus 4.7 (High) | 80.7 |
| 6 | Claude Opus 4.8 (High) | 78.95 |
| 7 | Kimi K2.6 (Thinking) | 75.93 |
| 8 | Gemma 4 31B | 75.44 |
| 9 | DeepSeek V4 Pro (Max) | 71.93 |
| 10 | GLM-5.1 | 70.18 |
| 11 | MiMo-V2.5-Pro | 69.64 |
| 12 | Ernie 5.1 | 68.42 |
| 13 | Spark X2 | 68.42 |
| 14 | Step 3.7 Flash | 66.67 |
| 15 | Qwen 3.6 Max (Preview) (Thinking) | 66.67 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-may-2026-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.