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

v0.1.53.364ac010a008浙ICP备09076226号-7

Back to benchmarks

Arena Agent Praise vs ComplaintAgents

Results for 52 models collected from 4 public sources.

Ranking Sources

#ModelScore

1

Claude Fable 5Anthropic · High mode

30.7%

2

GPT-5.6 SolOpenAI · xHigh mode

23.3%

3

Claude Opus 4.8Anthropic · Thinking mode

22.3%

4

Claude Opus 5Anthropic · High mode

21.8%

5

Kimi K3Moonshot · Max mode

20.2%

6

GLM-5.2Zhipu AI · Max mode

15.4%

7

Claude Sonnet 5Anthropic · High mode

15.3%

8

Gemini 3.8 FlashGoogle · High mode

14.8%

9

GPT-5.5OpenAI · xHigh mode

14.1%

10

Claude Opus 4.7Anthropic

13.7%

52 models total