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

INCLUDEMultilingual

Results for 69 models collected from 4 public sources.

#ModelScore

1

Gemini 2.5 ProGoogle

85.1%

2

OpenAI o1OpenAI

84.6%

3

DeepSeek-R1DeepSeek

82.7%

4

Qwen3-235B-A22B-Thinking-2507Alibaba

81.0%

5

Llama 4 MaverickMeta

80.9%

6

Qwen3-235B-A22B-Instruct-2507Alibaba

79.5%

7

GPT-4oOpenAI

78.8%

8

Qwen3-235B-A22BAlibaba

78.7%

9

DeepSeek-V3DeepSeek

76.7%

10

DeepSeek-V3 BaseDeepSeek

75.2%

69 models total