Every AI leaderboard

28 leaderboards · 992 models ranked

GSM8K what it measures, how it is scored and who leads it

Math · OpenAI · introduced Oct 27, 2021 · Accuracy · saturated

About this benchmark

Task
Solve grade-school math word problems that take two to eight steps.
Dataset
8,500 linguistically diverse problems written by people, with a 1,319-problem test set.
Method
Free-form answer; the final number is compared with the key.
Metric
Accuracy
Organization
OpenAI
Introduced
Oct 27, 2021

Versions

Newest first. New versions are added, never rewritten.

VersionDate
1Released with the paper.Oct 27, 20215 years ago

Sources: each benchmark's paper (arXiv) and its official site or leaderboard. Scores are the boards captured here every day, exactly as published.