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

v0.1.60.46f2d15f9eca浙ICP备09076226号-7

Back to benchmarks

Agents' Last ExamAgentsReasoning

Results for 35 models collected from 17 public sources.

Ranking Sources

#ModelScore

1

GPT-6 AstraOpenAI

59.3%

2

GPT-6 SolOpenAI · max

56.4%

3

Claude Opus 5Anthropic

55.5%

4

GPT-5.6 SolOpenAI

53.6%

5

GPT-5.6 TerraOpenAI

50.4%

6

GPT-5.6 LunaOpenAI

50.3%

7

Claude Fable 5Anthropic

48.7%

8

GPT-5.5OpenAI

46.9%

9

Claude Opus 4.8Anthropic

45.2%

10

Gemini 4 ArgonGoogle

39.5%

35 models total