What does GSM8K measure?
GSM8K measures multi-step mathematical reasoning on grade-school word problems. It is especially useful for spotting arithmetic mistakes, missed quantities, and broken chains of reasoning.
Upstream publisher OpenAIopenai/grade-school-math
A friendly, practical test of whether an AI model can solve multi-step grade-school math word problems without losing track of the numbers.
WHAT THIS PROJECT MEASURES
GSM8K contains linguistically diverse grade-school math problems that usually require two to eight steps to solve. It is useful for measuring whether a model can preserve quantities and operations across a short chain of reasoning.
This Trunchbull release exposes a fixed public sampler with an exact numeric-answer grader. The upstream source remains authoritative; the release records the source version and evaluation contract used by the demo.
IN PLAIN ENGLISH
GSM8K is a simple benchmark to understand and a useful one to run: give a model a word problem, let it work through the arithmetic, and check whether the final number is right. Trunchbull CI turns that familiar test into a reproducible release with visible grading.
EXECUTION CONTRACT
Runs in the standard chat lane with no tools or sandbox environment.
QUICK ANSWERS
GSM8K measures multi-step mathematical reasoning on grade-school word problems. It is especially useful for spotting arithmetic mistakes, missed quantities, and broken chains of reasoning.
The Trunchbull release uses exact numeric-answer grading, so a result passes when its normalized final answer matches the published answer.
TRUNCHBULL AVAILABILITY
Trunchbull port
Trunchbull maintains a runnable twenty-case demo port with a pinned numeric-answer grader.
3 CASES
gsm8k/natalia-clips
Multi-step addition after calculating a fractional value.
gsm8k/robe-fabric
Unit multiplication and subtraction across two quantities.
gsm8k/duck-eggs
Daily production, household use, and revenue calculation.
0 REQUESTED TOOLS
No model tools required.
Evaluation happens through the prompt and grader contract for this release.
MACHINE-READABLE PROVENANCE
{
"name": "GSM8K",
"catalogOwner": null,
"source": {
"url": "https://github.com/openai/grade-school-math",
"version": "test split · fixed sampler",
"commit": "main-2026-04-08",
"license": "MIT"
},
"port": null,
"release": {
"digest": "sha256:5e1c…9c02",
"lane": "chat",
"sandboxRequired": false
},
"cases": [
"gsm8k/natalia-clips",
"gsm8k/robe-fabric",
"gsm8k/duck-eggs"
],
"tools": []
}BUILD ON THIS PROJECT