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

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Back to benchmarks

Arena Agent Bash RecoveryAgents

Results for 31 models collected from 2 public sources.

#ModelScore

1

GPT-5.5OpenAI · xHigh mode

14.5%

2

Claude Opus 4.7Anthropic · Thinking mode

13.5%

3

Claude Opus 4.6Anthropic

11.8%

4

Claude Sonnet 4.6Anthropic

11.6%

5

GPT-5.4OpenAI · High mode

11.3%

6

Claude Opus 4.8Anthropic · Thinking mode

9.9%

7

Grok 4.5xAI

9.7%

8

Claude Sonnet 5Anthropic · High mode

9.6%

9

Claude Fable 5Anthropic · High mode

9.4%

10

GPT-5.6 SolOpenAI · xHigh mode

7.5%

31 models total