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

v0.1.60.46f2d15f9eca浙ICP备09076226号-7

Back to benchmarks

Terminal-Bench 4.0CodingAgents

Official website

Results for 21 models collected from 10 public sources.

Ranking Sources

#ModelScore

1

Claude Sonnet 5.5Anthropic

70.6%

2

Claude Opus 5.5Anthropic

66.4%

3

GPT-6 AstraOpenAI

58.2%

4

Claude Fable 5.1Anthropic

57.9%

5

Gemini 4 ArgonGoogle

57.4%

6

Claude Opus 5Anthropic

52.3%

7

Claude Fable 5Anthropic

42.4%

8

GPT-5.6 SolOpenAI

39.9%

9

Claude Haiku 5.5Anthropic

39.2%

10

Grok 4.7xAI

38.0%

21 models total