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

Loading page content

Local

Frontier models that can run locally and have fewer than 40 billion parameters.Updated 07/22, 03:19

#ModelScore

1

Qwen3.6-27BAlibaba

100.0

2

Qwen3.5-27BAlibaba

93.8

3

Qwen3.6-35B-A3BAlibaba

93.2

4

Qwen3-30B-A3B-Thinking-2507Alibaba

89.7

5

Gemma 4 31BGoogle

89.7

6

Qwen3.5-35B-A3BAlibaba

87.6

7

Qwen3-32BAlibaba

86.1

8

Qwen3.5-9BAlibaba

85.5

9

Gemma 4 26B A4BGoogle

85.2

10

Qwen3-14BAlibaba

84.2

47 models total