SuperCLUE General (March 2026) - Math Reasoning: leaderboard
SuperCLUE general leaderboard, March 2026 edition (2026年3月): 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: Estimated already saturated. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (High) | 92.44 | #64 (Gemini 3.1 Pro (Preview)) |
| 2 | DeepSeek V4 Flash (Max) | 89.08 | #155 (DeepSeek V4 Flash) |
| 3 | GPT-5.4 (xHigh) | 88.89 | #83 (GPT-5.4) |
| 4 | DeepSeek V4 Pro (Max) | 87.39 | #112 (DeepSeek V4 Pro) |
| 5 | Claude Opus 4.6 (Max) | 85.71 | #67 (Claude Opus 4.6) |
| 6 | Grok 4.20 Beta (0309) (Reasoning) | 85.71 | #198 (Grok 4.20 Beta (0309)) |
| 7 | Gemini 3 Flash (Preview) (High) | 85.71 | #90 (Gemini 3 Flash (Preview)) |
| 8 | Qwen 3.5 397B A17B (Thinking) | 84.87 | #154 (Qwen 3.5 397B A17B) |
| 9 | Doubao-Seed-2-0-Pro-260215 (High) | 84.87 | |
| 10 | MiMo-V2-Pro | 84.03 | #177 |
| 11 | Qwen 3.5 122B A10B (Thinking) | 82.35 | #184 (Qwen 3.5 122B A10B) |
| 12 | Kimi K2.5 (Thinking) | 81.51 | #152 (Kimi K2.5) |
| 13 | Step 3.5 Flash | 80.67 | #281 |
| 14 | GPT-OSS-120B (High) | 79.83 | #346 (GPT-OSS-120B) |
| 15 | MiniMax-M2.7 | 78.15 | #270 |
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-march-2026-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.