benchmark
GSM8K
Metadata
| Source Table | benchmarks |
| Source ID | fjjBrOI3p2 |
| Description | Grade School Math 8K — a dataset of 8,500 linguistically diverse grade-school math word problems requiring multi-step reasoning with basic arithmetic operations. |
| Wiki ID | gsm8k |
| Children | — |
| Created | Mar 24, 2026, 11:23 PM |
| Updated | Mar 24, 2026, 11:24 PM |
| Synced | Mar 24, 2026, 11:24 PM |
Record Data
id | fjjBrOI3p2 |
slug | gsm8k |
name | GSM8K |
category | math |
description | Grade School Math 8K — a dataset of 8,500 linguistically diverse grade-school math word problems requiring multi-step reasoning with basic arithmetic operations. |
website | — |
scoringMethod | accuracy |
higherIsBetter | Yes |
introducedDate | 2021-10 |
maintainer | OpenAI |
source | arxiv.org/abs/2110.14168 |
Debug info
Thing ID: fjjBrOI3p2
Source Table: benchmarks
Source ID: fjjBrOI3p2
Wiki ID: gsm8k