porchbench is an open-source CLI tool designed for rigorous benchmarking and evaluation of local large language models (LLMs). It provides paired statistics, LLM-as-judge scoring, and ensures reproducible runs, making it ideal for AI researchers and developers who need to assess the quality and performance of local AI models. The tool supports integration with local inference engines such as Ollama and quantized models.
porchbench is a LLM eval & observability project. It enables developers to rigorously benchmark and evaluate the quality of local LLMs with reproducible and automated scoring. It is built as an open-source project for AI researchers and developers working with local language models. porchbench is open source under the Apache-2.0 license. It runs on the command line, and it can be self-hosted.
Behind porchbench is mmdevelops, and it first shipped in 2026. Development happens publicly on GitHub with 138 commits in the last 90 days. Among its 6 catalogued features are paired statistics, LLM-as-judge scoring, and reproducible runs.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do