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

ToolathlonAgents

Official website

Results for 26 models collected from 8 public sources.

#ModelScore

1

Claude Fable 5Anthropic

61.7%

2

Claude Mythos PreviewAnthropic

61.1%

3

Claude Opus 4.8Anthropic

59.9%

4

GPT-5.6 SolOpenAI

58.0%

5

55.6%

6

54.6%

7

GPT-5.6 LunaOpenAI

53.4%

8

GPT-5.6 TerraOpenAI

53.1%

9

GPT-5.3-CodexOpenAI

51.9%

10

DeepSeek-V4-ProDeepSeek

51.8%

26 models total