Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

Loading page content

© 2026 Leaderboard.cn. Traceable AI model evaluations and rankings.

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

FRAMESReasoning

Results for 9 models collected from 2 public sources.

#ModelScore

1

DeepSeek-R1DeepSeek

82.5%

2

GPT-4oOpenAI

80.5%

3

OpenAI o1-miniOpenAI

76.9%

4

DeepSeek-V3DeepSeek

73.3%

5

Claude 3.5 Sonnet 20241022Anthropic

72.5%

6

Llama 3.1 405B InstructMeta

70.0%

7

Qwen2.5-72BAlibaba

69.8%

8

DeepSeek-V2-0506DeepSeek

66.9%

9

DeepSeek-V2.5-0905DeepSeek

65.4%

9 models total