Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

Loading page content

© 2026 Leaderboard.cn. Traceable AI model evaluations and rankings.

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

Terminal Bench 2.1 (Terminus-2)Coding

Official website

Results for 20 models collected from 6 public sources.

#ModelScore

1

Claude Fable 5Anthropic

88.0%

2

Claude Opus 4.8Anthropic

85.0%

3

84.0%

4

GLM-5.2Zhipu AI

81.0%

5

Claude Sonnet 5Anthropic

80.4%

6

Qwen3.7-MaxAlibaba

75.0%

7

Gemini 3.1 ProGoogle

74.0%

8

Hunyuan 3Tencent

71.7%

9

Seed2.1 ProByteDance

71.0%

10

Kimi-K2.6Moonshot AI

67.2%

20 models total