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-bench ProCoding

Official website

Results for 46 models collected from 22 public sources.

#ModelScore

1

Claude Fable 5Anthropic

80.4%

2

Claude Mythos PreviewAnthropic

77.8%

3

Claude Opus 4.8Anthropic

69.2%

4

64.7%

5

GPT-5.6 SolOpenAI

64.6%

6

Claude Opus 4.7Anthropic

64.3%

7

GPT-5.6 TerraOpenAI

63.4%

8

Claude Sonnet 5Anthropic

63.2%

9

GPT-5.6 LunaOpenAI

62.7%

10

GLM-5.2Zhipu AI

62.1%

46 models total