DataLearner logoDataLearnerAI
AI Tech Blogs
Leaderboards
Benchmarks
Models
Resources
Tool Directory

加载中...

DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

产品

  • Leaderboards
  • 模型对比
  • Datasets

资源

  • Tutorials
  • Editorial
  • Tool directory

关于

  • 关于我们
  • 隐私政策
  • 数据收集方法
  • 联系我们

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

隐私政策服务条款
Back to Main Leaderboard

大模型数学推理能力评测排行榜

本页面提供最新、最全面的大模型数学推理能力评测排行榜。我们通过 GSM8K、MATH、AIME 2025 等多个权威数学基准数据集,对包括 OpenAI 的 GPT-4o、Anthropic 的 Claude、阿里巴巴的 Qwen、DeepSeek-R1 等模型进行评测。

Updated on: 2025-07-20 20:56:42

Benchmark switcher

Pick the leaderboard to sync both chart and table

AIME2025AIME 2024MATH-500GSM8K

Filters

Active
All3B and below7B13B34B65B100B and above
AllReasoning ModelsFoundation ModelsInstruction/Chat ModelsCoding Models

LLM Performance Results

Data source: DataLearnerAI
No chart data available
RankModelAIME2025AIME 2024MATH-500GSM8KParams (B)License
1Phi-4-mini-instruct (3.8B)0.0010.0071.8088.6038BFree commercial
2Qwen2.5-3B0.000.000.0079.1030BFree commercial
3Llama-3.2-3B0.000.000.0034.0032BFree commercial
4Phi-4-instruct (reasoning-trained)0.0050.0090.400.0038B不开源
1
Phi-4-mini-instruct (3.8B)
38B
AIME20250.00
AIME 202410.00
MATH-50071.80
GSM8K88.60
Free commercial
2
Qwen2.5-3B
30B
AIME20250.00
AIME 20240.00
MATH-5000.00
GSM8K79.10
Free commercial
3
Llama-3.2-3B
32B
AIME20250.00
AIME 20240.00
MATH-5000.00
GSM8K34.00
Free commercial
4
Phi-4-instruct (reasoning-trained)
38B
AIME20250.00
AIME 202450.00
MATH-50090.40
GSM8K0.00
不开源