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

AlpacaEval 2.0 LC win rateConversation

Results for 8 models collected from 2 public sources.

#ModelScore

1

DeepSeek-R1DeepSeek

87.6%

2

DeepSeek-V3DeepSeek

70.0%

3

OpenAI o1-miniOpenAI

57.8%

4

Claude 3.5 Sonnet 20241022Anthropic

52.0%

5

GPT-4oOpenAI

51.1%

6

DeepSeek-V2.5-0905DeepSeek

50.5%

7

Qwen2.5-72BAlibaba

49.1%

8

Llama 3.1 405B InstructMeta

40.5%

8 models total