Skip to content
Longterm Wiki
benchmark-result

Gemini on MMLU-Pro: 90.99

Child of MMLU-Pro

Metadata

Source Tablebenchmark_results
Source IDsjzbkK1xEy
ParentMMLU-Pro
Children
CreatedApr 24, 2026, 6:59 PM
UpdatedApr 24, 2026, 6:59 PM
SyncedApr 24, 2026, 6:59 PM

Record Data

idsjzbkK1xEy
benchmarkId3PM0ZfVJxU
modelIdGemini(ai-model)
score90.99
unitpercent
date2026-02-26
sourceUrl
notesGemini 3.1 Pro Preview leads MMLU-Pro benchmark

Source Check Verdicts

confirmed98% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: sjzbkK1xEy

Source Table: benchmark_results

Source ID: sjzbkK1xEy

Parent Thing ID: 3PM0ZfVJxU