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

v0.1.53.364ac010a008浙ICP备09076226号-7

Loading page content

Agents

Covers tool use, web browsing, and long-horizon task execution.Updated 09/10, 21:09

#ModelScore

1

Claude Fable 5.1Anthropic

100.0

2

GPT-6 AstraOpenAI

99.9

3

Claude Fable 5Anthropic

99.6

4

Claude Opus 5Anthropic

98.2

5

GPT-5.6 SolOpenAI

95.5

6

DeepSeek-V4.1-FlashDeepSeek

94.8

7

Kimi K3Moonshot AI

93.6

8

Muse Spark 1.3Meta

93.0

9

Claude Opus 4.8Anthropic

90.0

10

GPT-5.5 ProOpenAI

88.6

148 models total