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 (Humanity's Last Exam)Reasoning

Official website

Results for 57 models collected from 22 public sources.

#ModelScore

1

Claude Opus 4.8Anthropic

49.8%

2

46.9%

3

Claude Opus 4.7Anthropic

46.9%

4

Gemini 3.1 ProGoogle

45.0%

5

GPT-5.5 ProOpenAI

43.1%

6

GPT-5.4 ProOpenAI

42.7%

7

Qwen3.7-MaxAlibaba

41.4%

8

GLM-5.2Zhipu AI

40.5%

9

Claude Opus 4.6Anthropic

40.0%

10

39.8%

57 models total