SuperCLUE General (March 2025) - Math Reasoning: leaderboard

Metric: Score. Source: www.superclueai.com. 36 models tracked.

Top models

#ModelScore
1O3 Mini (High)94.74
2QwQ-32B88.6
3DeepSeek R185.96
4DeepSeek R1 Distill Qwen 32B85.85
5Gemini 2.0 Flash (01-21) (Thinking)83.33
6DeepSeek R1 Distill Qwen 14B79.46
7Claude 3.7 Sonnet78.07
8DeepSeek-R1-Distill-Qwen-7B77.23
9GLM-Zero-Preview74.56
10GPT-4.5 (Preview)67.54
11Gemini 2.0 Pro (Preview 02-05)65.79
12Doubao-1.5-pro-32k-25011562.28
13DeepSeek V348.25
14hunyuan-turbos-2025022647.37
15DeepSeek R1 Distill Qwen 1.5B37.72

Interactive version: theaggregate.ai/benchmark?slug=superclue-general-march-2025-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.