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

v0.1.60.46f2d15f9eca浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

ExploitBench (Cap%)CybersecurityAgents

Official website

Results for 19 models collected from 7 public sources.

Ranking Sources

#ModelScore

1

GPT-6 AstraOpenAI · max

100.0%

2

GPT-6.1 SolOpenAI · max

99.7%

3

GPT-6 SolOpenAI · max

81.7%

4

GPT-5.6 SolOpenAI

78.5%

5

Claude Fable 5Anthropic

78.0%

6

Claude Mythos PreviewAnthropic

74.2%

7

Claude Opus 5Anthropic

70.0%

8

GLM-5.3Zhipu AI

54.4%

9

GPT-5.6 TerraOpenAI

52.9%

10

MiMo-V2.6-ProXiaomi

47.9%

19 models total