evalforge

EvalForge – AI Evaluation & Testing Platform

EvalForge is a full-stack AI evaluation and testing platform designed to evaluate, benchmark, and compare AI models using real test cases and structured evaluation metrics. It supports local AI models through Ollama and cloud-based models through Groq, with automated evaluation methods including Exact Match, Keyword Match, and rubric-based scoring. The platform provides a centralized dashboard for running evaluations, analyzing results, comparing model performance, and tracking evaluation history.

Built with a focus on backend engineering, software testing, and AI quality assessment.