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

Arena-HardConversation

Results for 39 models collected from 3 public sources.

#ModelScore

1

Gemini 2.5 ProGoogle

96.4%

2

Qwen3-235B-A22BAlibaba · Non-reasoning mode

96.1%

3

Qwen3-32BAlibaba

93.8%

4

DeepSeek-R1DeepSeek

92.3%

5

OpenAI o1OpenAI

92.1%

6

OpenAI o1-miniOpenAI

92.0%

7

Qwen3-14BAlibaba

91.7%

8

Qwen3-30B-A3BAlibaba

91.0%

9

QwQ-32BAlibaba

89.5%

10

o3-miniOpenAI

89.0%

39 models total