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

FrontierMath Tier 4Reasoning

Results for 14 models collected from 4 public sources.

#ModelScore

1

Claude Fable 5Anthropic

87.8%

2

72.5%

3

GPT-5.6 TerraOpenAI

68.3%

4

GPT-5.6 SolOpenAI

65.9%

5

GPT-5.6 LunaOpenAI

58.5%

6

Claude Opus 4.8Anthropic

56.1%

7

GPT-5.5 ProOpenAI

39.6%

8

GPT-5.4 ProOpenAI

38.0%

9

GPT-5.2 ProOpenAI

31.3%

10

27.1%

14 models total