# GSM8K

GSM8K is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Tests multi-step arithmetic reasoning on human-written grade-school math word problems.

## Details

- Address: Online, Global
- Website: [github.com/openai/grade-school-math](<https://github.com/openai/grade-school-math>)
- Tags: Helpful, Science
- Category: Math
- Status: Active
- Data licence: MIT
- Data access: open
- Grader: exact
- Organization: OpenAI
- Released: 2021-10
- Paper: [arxiv.org/abs/2110.14168](<https://arxiv.org/abs/2110.14168>)
- Repository: [github.com/openai/grade-school-math](<https://github.com/openai/grade-school-math>)
- Task count: 8,500
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is GSM8K?

GSM8K is at Online, Global.

### How do I contact GSM8K?

To contact GSM8K, visit https://github.com/openai/grade-school-math.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/gsm8k>)
- [Math in Online](<https://aibenchmarkindex.com/global/online/category/math.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.