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

GSM8K

benchmark

Metadata

Source Tablebenchmarks
Source IDfjjBrOI3p2
DescriptionGrade School Math 8K — a dataset of 8,500 linguistically diverse grade-school math word problems requiring multi-step reasoning with basic arithmetic operations.
Wiki IDgsm8k
Children—
CreatedMar 24, 2026, 11:23 PM
UpdatedMar 24, 2026, 11:24 PM
SyncedMar 24, 2026, 11:24 PM

Record Data

idfjjBrOI3p2
sluggsm8k
nameGSM8K
categorymath
subCategory—
descriptionGrade School Math 8K — a dataset of 8,500 linguistically diverse grade-school math word problems requiring multi-step reasoning with basic arithmetic operations.
website—
scoringMethodaccuracy
higherIsBetterYes
introducedDate2021-10
maintainerOpenAI
sourcearxiv.org/abs/2110.14168
Debug info

Thing ID: fjjBrOI3p2

Source Table: benchmarks

Source ID: fjjBrOI3p2

Wiki ID: gsm8k