# EvalPlus

> Code-generation evaluation framework with expanded HumanEval+/MBPP+ tests and EvalPerf for checking correctness and runtime efficiency.

- id: `evalplus`
- category: Evals & Observability (`evals-observability`)
- url: https://github.com/evalplus/evalplus
- repo: https://github.com/evalplus/evalplus
- status: active
- pricing: open-source
- license: Apache-2.0
- tags: code-evaluation, correctness, efficiency, python
- auth: none
- access notes: Python CLI/package: pip install evalplus; model backend and isolated code-execution environment configured separately.
- sources: https://github.com/evalplus/evalplus , https://github.com/evalplus/evalplus/blob/master/LICENSE , https://huggingface.co/datasets/evalplus/humanevalplus , https://pypi.org/project/evalplus/
- added: 2026-11-08
- updated: 2026-11-08
- last verified: 2026-11-08
- featured in: Code-generation evals compared — EvalPlus, BigCodeBench and LiveCodeBench (https://indexagentica.com/compare/code-generation-eval-benchmarks/)
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/evalplus/
- json: https://indexagentica.com/api/entries/evalplus.json

Public Apache-2.0 framework, available as evalplus (PyPI 0.3.1; Python 3.9+). Supports generation, post-processing and evaluation over HumanEval+/MBPP+ and efficiency evaluation with EvalPerf. README includes local and Docker execution paths; generated code is untrusted and should be evaluated in isolated environments. Inference and execution resources are separate. The linked HumanEval+ dataset card also declares Apache-2.0.
