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

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Back to benchmarks

GDPval-AA v2ReasoningAgents

Results for 10 models collected from 2 public sources.

#ModelScore

1

Claude Fable 5Anthropic

1,760.0pts

2

GPT-5.6 SolOpenAI

1,748.0pts

3

Kimi K3Moonshot AI

1,668.0pts

4

Claude Opus 4.8Anthropic

1,600.1pts

5

GPT-5.6 TerraOpenAI

1,593.0pts

6

GPT-5.6 LunaOpenAI

1,591.8pts

7

GLM-5.2Zhipu AI

1,514.0pts

8

GPT-5.5OpenAI

1,494.0pts

9

Gemini 3.5 FlashGoogle

1,348.8pts

10

Gemini 3.1 ProGoogle

962.3pts

10 models total