Skip to content
Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.
Longterm Wiki

MGSM

benchmark

Metadata

Source Tablebenchmarks
Source IDkNb3n2XMUI
DescriptionMultilingual Grade School Math — a benchmark of 250 grade-school math problems translated into 10 typologically diverse languages. Tests multilingual mathematical reasoning.
Wiki IDmgsm
Children—
CreatedMar 14, 2026, 12:43 AM
UpdatedMar 24, 2026, 11:24 PM
SyncedMar 24, 2026, 11:24 PM

Record Data

idkNb3n2XMUI
slugmgsm
nameMGSM
categorymath
subCategory—
descriptionMultilingual Grade School Math — a benchmark of 250 grade-school math problems translated into 10 typologically diverse languages. Tests multilingual mathematical reasoning.
website—
scoringMethodaccuracy
higherIsBetterYes
introducedDate2022-10
maintainerGoogle Research
sourcearxiv.org/abs/2210.03057
Debug info

Thing ID: kNb3n2XMUI

Source Table: benchmarks

Source ID: kNb3n2XMUI

Wiki ID: mgsm