SuperCLUE General (2025 Annual) - Math Reasoning: leaderboard
SuperCLUE general leaderboard, 2025 Annual edition (2025年度测评): math reasoning (数学推理) score from the 总排行榜 sheet. SuperCLUE's periodic Chinese-language general evaluation uses a new question set each edition, so editions are separate boards. Score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around February 2027. 34 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Doubao-Seed-2.0-Pro-260215 | 87.83 | #86 |
| 2 | Gemini 3.1 Pro (Preview) (High) | 84.96 | #64 (Gemini 3.1 Pro (Preview)) |
| 3 | Gemini 3 Pro (Preview) | 80.87 | #71 |
| 4 | Qwen 3 Max (Thinking) | 80.87 | #213 (Qwen 3 Max) |
| 5 | Gemini 3 Flash (Preview) | 79.13 | #90 |
| 6 | Qwen 3.5 27B (Thinking) | 78.26 | #192 (Qwen 3.5 27B) |
| 7 | Qwen 3.5 397B A17B (Thinking) | 78.26 | #154 (Qwen 3.5 397B A17B) |
| 8 | Claude Opus 4.6 (High) | 77.88 | #67 (Claude Opus 4.6) |
| 9 | Kimi K2.5 (Thinking) | 77.39 | #152 (Kimi K2.5) |
| 10 | Qwen 3.5 35B A3B (Thinking) | 76.52 | #268 (Qwen 3.5 35B A3B) |
| 11 | Step 3.5 Flash | 75.65 | #281 |
| 12 | Qwen 3.5 122B A10B (Thinking) | 75.65 | #184 (Qwen 3.5 122B A10B) |
| 13 | Grok 4 | 74.78 | #189 |
| 14 | GLM-5 | 73.91 | #149 |
| 15 | GPT-OSS-120B (High) | 73.91 | #346 (GPT-OSS-120B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-2025-annual-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.