evalplus
Rigorous evaluation of LLM-synthesised code (HumanEval+, MBPP+)
homepage ↗homepage ↗ pypi: evalplus github: evalplus/evalplus
Available in
| Overlay | Newest | Ebuilds | Last activity | |
|---|---|---|---|---|
| stuff GitHub ↗ | 0.3.1 | 1 | 2 d | details › |
Versions & arches
Use flags of 0.3.1
- perf Pull dev-python/cirron and dev-python/pympler for the evalperf-style perf-counter evaluation