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

v0.1.53.364ac010a008浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

CyberGymCodingAgents

Official website

Results for 28 models collected from 9 public sources.

Ranking Sources

#ModelScore

1

DeepSeek-V4.1-FlashDeepSeek

88.1%

2

GLM-5.3Zhipu AI

84.5%

3

GPT-5.6 SolOpenAI

84.5%

4

Claude Fable 5Anthropic

83.8%

5

DeepSeek-V4-Pro-0813DeepSeek

83.3%

6

Claude Opus 4.8Anthropic

83.1%

7

Claude Mythos PreviewAnthropic

83.0%

8

81.8%

9

GPT-5.6 TerraOpenAI

81.8%

10

Kimi K3Moonshot AI

80.0%

28 models total