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 Document RatingLong context

Official website

Results for 28 models collected from 2 public sources.

#ModelScore

1

Claude Opus 4.6Anthropic · Thinking mode

1,508.1Elo

2

Claude Fable 5Anthropic

1,507.1Elo

3

Claude Opus 4.7Anthropic · Thinking mode

1,504.5Elo

4

GPT-5.5OpenAI · High mode

1,488.2Elo

5

Claude Sonnet 4.6Anthropic

1,487.6Elo

6

Gemini 3.5 FlashGoogle

1,481.0Elo

7

Claude Opus 4.8Anthropic · Thinking mode

1,476.6Elo

8

Claude Sonnet 5Anthropic · Thinking mode

1,476.1Elo

9

GPT-5.4OpenAI

1,474.9Elo

10

Claude Opus 4.5Anthropic

1,461.4Elo

28 models total