Skip to content
Longterm Wiki
benchmark-result

Mistral on GSM8K: 40.3

Child of GSM8K

Metadata

Source Tablebenchmark_results
Source IDog4W7C5TMM
ParentGSM8K
Children
CreatedApr 24, 2026, 7:21 PM
UpdatedApr 24, 2026, 7:21 PM
SyncedApr 24, 2026, 7:21 PM

Record Data

idog4W7C5TMM
benchmarkIdfjjBrOI3p2
modelIdMistral(ai-model)
score40.3
unitpercent
date2023-09-27
sourceUrl
notesMistral 7B on GSM8K 8-shot

Source Check Verdicts

confirmed98% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: og4W7C5TMM

Source Table: benchmark_results

Source ID: og4W7C5TMM

Parent Thing ID: fjjBrOI3p2