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 Search RatingAgents

Official website

Results for 42 models collected from 2 public sources.

#ModelScore

1

claude-opus-4-6-searchAnthropic · Search mode

1,254.6Elo

2

Claude Opus 4.6Anthropic · Search mode

1,252.9Elo

3

GPT-5.5OpenAI · Search mode

1,240.1Elo

4

gpt-5.5-searchOpenAI · Search mode

1,239.1Elo

5

Claude Fable 5Anthropic

1,236.8Elo

6

Claude Opus 4.7Anthropic

1,235.0Elo

7

ERNIE 5.1Baidu

1,227.1Elo

8

claude-sonnet-4-6-searchAnthropic · Search mode

1,222.0Elo

9

Claude Sonnet 4.6Anthropic · Search mode

1,219.7Elo

10

Gemini 3.1 ProGoogle · Grounding mode

1,213.3Elo

42 models total