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

Terminal-Bench 2.0Coding

Results for 10 models collected from 4 public sources.

#ModelScore

1

GPT-5.5OpenAI

82.7%

2

GPT-5.3-CodexOpenAI

77.3%

3

GPT-5.4OpenAI

75.1%

4

Claude Opus 4.7Anthropic

69.4%

5

Gemini 3.1 ProGoogle

68.5%

6

GPT-5.2-CodexOpenAI

64.0%

7

GPT-5.2OpenAI

62.2%

8

GPT-5.4 miniOpenAI

60.0%

9

GPT-5.4 nanoOpenAI

46.3%

10

GPT-5 miniOpenAI

38.2%

10 models total