Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

leaderboard.cn

Benchmark details loading

Loading page content

About Ranking methodology Changelog

v0.1.66.c14ade6abf77浙ICP备09076226号-7

Back to benchmarks

CyberGymCybersecurityAgents

Official website

Results for 32 models collected from 11 public sources.

Ranking Sources

#ModelScore

1

MiMo-V2.6-FlashXiaomi

95.1%

2

MiMo-V2.6-ProXiaomi

94.0%

3

DeepSeek-V4.1-FlashDeepSeek

88.1%

4

GLM-5.3Zhipu AI

84.5%

5

GPT-5.6 SolOpenAI

84.5%

6

Claude Fable 5Anthropic

83.8%

7

DeepSeek-V4-Pro-0813DeepSeek

83.3%

8

Claude Opus 4.8Anthropic

83.1%

9

Claude Mythos PreviewAnthropic

83.0%

10

MiniMax M3.1 FlashMiniMax · Release table: 82.2; release prose: 82%.

82.2%

32 models total

Benchmark details loading

Back to benchmarks

CyberGymCybersecurityAgents

Official website

Results for 32 models collected from 11 public sources.

Ranking Sources

#ModelScore

1

MiMo-V2.6-FlashXiaomi

95.1%

2

MiMo-V2.6-ProXiaomi

94.0%

3

DeepSeek-V4.1-FlashDeepSeek

88.1%

4

GLM-5.3Zhipu AI

84.5%

5

GPT-5.6 SolOpenAI

84.5%

6

Claude Fable 5Anthropic

83.8%

7

DeepSeek-V4-Pro-0813DeepSeek

83.3%

8

Claude Opus 4.8Anthropic

83.1%

9

Claude Mythos PreviewAnthropic

83.0%

10

MiniMax M3.1 FlashMiniMax · Release table: 82.2; release prose: 82%.

82.2%

32 models total