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

HLE-FullReasoning

Official website

temperature=1.0, top_p=0.95

#ModelScore

1

Claude Fable 5Anthropic

59.0%

2

Claude Mythos PreviewAnthropic

56.8%

3

Muse Spark 1.1Meta

52.2%

4

Claude Opus 4.8Anthropic

49.8%

5

Gemini 3.1 ProGoogle

45.4%

6

44.8%

7

GPT-5.6 SolOpenAI

44.5%

8

Kimi K3Moonshot AI

43.5%

9

Claude Sonnet 5Anthropic

43.2%

10

42.8%

15 models total