modelscope /
evalscope
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
Updated 56 min ago
+42 stars gained this week
Stars gained each day, last 30 days
Usual pace · 4 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
EvalScope is a Python framework for evaluating large language, vision-language, and AIGC models on established benchmarks, and for stress-testing their inference performance. It is aimed at developers and researchers who need to measure model capabilities.
Summary written by AI from the repository’s description and README.
modelscope / evalscope
View on GitHub(opens in new tab)