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

SWE-MarathonCoding

Official website

Results for 10 models collected from 3 public sources.

#ModelScore

1

Kimi K3Moonshot AI

42.0%

2

Claude Opus 4.8Anthropic

40.0%

3

GPT-5.6 SolOpenAI

39.0%

4

Claude Fable 5Anthropic

35.0%

5

29.0%

6

Claude Opus 4.7Anthropic

16.0%

7

14.0%

8

GLM-5.2Zhipu AI

13.0%

9

Gemini 3.1 ProGoogle

4.0%

10

GLM-5.1Zhipu AI

1.0%

10 models total