Skip to content
Longterm Wiki
Index
Benchmark Result·guBxl9AmRz·Record·Profile

sid_PaKhQQNPkg / GPQA Diamond: 94.3

Verdictconfirmed98%
· 4/24/2026

Inline sourcing: confirmed

Our claim

entire record
Benchmark
bdDmOTMoX8
Model
Gemini
Score
94.3
Unit
percent
Date
February 19, 2026
Notes
Gemini 3.1 Pro achieves highest recorded score on GPQA Diamond

Source evidence

0 src · 0 checks

No evidence on file.

Case № guBxl9AmRzFiled 4/24/2026Confidence 98%
Source Check: sid_PaKhQQNPkg / GPQA Diamond: 94.3 | Longterm Wiki