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 2.0 (Terminus-2)Coding

Official website

Results for 29 models collected from 13 public sources.

#ModelScore

1

75.1%

2

Qwen3.7-PlusAlibaba

70.3%

3

Qwen3.7-MaxAlibaba

69.7%

4

Gemini 3.1 ProGoogle

68.5%

5

DeepSeek-V4-ProDeepSeek

67.9%

6

Kimi-K2.6Moonshot AI

66.7%

7

MiMo-V2.5Xiaomi

65.8%

8

Claude Opus 4.6Anthropic

65.4%

9

GLM-5.1Zhipu AI

63.5%

10

Qwen3.6-PlusAlibaba

61.6%

29 models total