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

v0.1.53.364ac010a008浙ICP备09076226号-7

Back to benchmarks

ExploitBench (Cap%)Agents

Official website

Results for 13 models collected from 4 public sources.

Ranking Sources

#ModelScore

1

GPT-6 AstraOpenAI

100.0%

2

GPT-5.6 SolOpenAI

78.5%

3

Claude Fable 5Anthropic

78.0%

4

Claude Mythos PreviewAnthropic

74.2%

5

Claude Opus 5Anthropic

70.0%

6

GLM-5.3Zhipu AI

54.4%

7

GPT-5.6 TerraOpenAI

52.9%

8

GPT-5.5OpenAI

47.9%

9

Claude Opus 4.8Anthropic

40.0%

10

GPT-5.6 LunaOpenAI

33.2%

13 models total