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

Arena Agent Bash RecoveryAgents

Results for 52 models collected from 4 public sources.

Ranking Sources

#ModelScore

1

Claude Opus 5Anthropic · Max mode

15.5%

2

GPT-5.5OpenAI · xHigh mode

14.5%

3

Claude Fable 5Anthropic · High mode

13.7%

4

Claude Opus 4.7Anthropic · High mode

13.5%

5

Claude Opus 4.6Anthropic

11.8%

6

inkling-smallThinky

11.7%

7

Claude Sonnet 4.6Anthropic

11.6%

8

GPT-5.6 LunaOpenAI · xHigh mode

11.3%

9

GPT-5.4OpenAI · High mode

11.3%

10

Claude Sonnet 5Anthropic · High mode

11.0%

52 models total

Benchmark details loading

Back to benchmarks

Arena Agent Bash RecoveryAgents

Results for 52 models collected from 4 public sources.

Ranking Sources

#ModelScore

1

Claude Opus 5Anthropic · Max mode

15.5%

2

GPT-5.5OpenAI · xHigh mode

14.5%

3

Claude Fable 5Anthropic · High mode

13.7%

4

Claude Opus 4.7Anthropic · High mode

13.5%

5

Claude Opus 4.6Anthropic

11.8%

6

inkling-smallThinky

11.7%

7

Claude Sonnet 4.6Anthropic

11.6%

8

GPT-5.6 LunaOpenAI · xHigh mode

11.3%

9

GPT-5.4OpenAI · High mode

11.3%

10

Claude Sonnet 5Anthropic · High mode

11.0%

52 models total