SuperCLUE General (2025 Annual) - Math Reasoning: leaderboard
Metric: Score. Source: www.superclueai.com. 34 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-Seed-2.0-Pro-260215 | 87.83 |
| 2 | Gemini 3.1 Pro (Preview) (High) | 84.96 |
| 3 | Gemini 3 Pro (Preview) | 80.87 |
| 4 | Qwen 3 Max (Thinking) | 80.87 |
| 5 | Gemini 3 Flash (Preview) | 79.13 |
| 6 | Qwen 3.5 27B (Thinking) | 78.26 |
| 7 | Qwen 3.5 397B A17B (Thinking) | 78.26 |
| 8 | Claude Opus 4.6 | 77.88 |
| 9 | Kimi K2.5 (Thinking) | 77.39 |
| 10 | Qwen 3.5 35B A3B (Thinking) | 76.52 |
| 11 | Step 3.5 Flash | 75.65 |
| 12 | Qwen 3.5 122B A10B (Thinking) | 75.65 |
| 13 | Grok 4 | 74.78 |
| 14 | GLM-5 | 73.91 |
| 15 | GPT-OSS-120B (High) | 73.91 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-2025-annual-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.