OpenAI's hand-crafted Python coding benchmark: 164 programming problems with function signatures, docstrings, and unit tests. Models are evaluated by Pass@k — the probability of generating at least one correct solution in k tries. The definitive benchmark for code generation ability.
Dataset Details
Provider
OpenAI
Category
Evaluation & Benchmarks
Size
164 Problems
License
MIT
Downloads
5M
Tags
Benchmark, Python, Code-Correctness, Unit-Tests
from datasets import load_dataset
ds = load_dataset("openai/openai_humaneval")
Related datasets
SWE-bench — Benchmarking real-world software engineering - never train on it
MT-Bench — Judging multi-turn chat quality with LLM-as-judge
Frequently asked questions
Can I use HumanEval commercially?
Yes — HumanEval is released under MIT, a permissive license that allows commercial use, including training models you ship in a product. Check the dataset card for attribution requirements before release.
How much data does HumanEval contain, and do I need all of it?
HumanEval contains 164 Problems. It is an evaluation benchmark, so it is used in full to measure models — never mix it into training data, or your benchmark scores become meaningless.
What is HumanEval best used for?
Benchmarking Python code generation - never train on it. It belongs to the Evaluation & Benchmarks section of our dataset hub, where you'll find alternatives and complementary sets.