Skip to content
Longterm Wiki
benchmark-result

Gemini on GPQA Diamond: 94.3

Child of GPQA Diamond

Metadata

Source Tablebenchmark_results
Source IDguBxl9AmRz
ParentGPQA Diamond
Children
CreatedApr 24, 2026, 6:59 PM
UpdatedApr 24, 2026, 6:59 PM
SyncedApr 24, 2026, 6:59 PM

Record Data

idguBxl9AmRz
benchmarkIdbdDmOTMoX8
modelIdGemini(ai-model)
score94.3
unitpercent
date2026-02-19
sourceUrl
notesGemini 3.1 Pro achieves highest recorded score on GPQA Diamond

Source Check Verdicts

confirmed98% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: guBxl9AmRz

Source Table: benchmark_results

Source ID: guBxl9AmRz

Parent Thing ID: bdDmOTMoX8