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

GPQA-DiamondReasoning

Official website

Results for 126 models collected from 38 public sources.

#ModelScore

1

GPT-5.6 SolOpenAI

94.6%

2

Claude Mythos PreviewAnthropic

94.6%

3

GPT-5.4 ProOpenAI

94.4%

4

Gemini 3.1 ProGoogle

94.3%

5

Claude Opus 4.7Anthropic

94.2%

6

93.6%

7

Claude Opus 4.8Anthropic

93.6%

8

Kimi K3Moonshot AI

93.5%

9

GPT-5.2 ProOpenAI

93.2%

10

MiniMax M3MiniMax

93.0%

126 models total