g-eval

A framework for evaluating large language models (LLMs) across a variety of tasks.

Production-grade LLM-as-Judge evaluation framework with position, verbosity & self-enhancement bias mitigation. FastAPI + Streamlit + Python SDK.

Refactored Python package for evaluating AI-generated lecture summaries using ROUGE, G-Eval and statistical analysis.

Production-grade open-source LLM evaluation platform with G-Eval, LLM-as-a-Judge, RAG evaluation, and customizable AI evaluation pipelines.

제 8회 미래에셋증권 X 네이버클라우드 AI/Data 페스티벌

This repository provides a solution for generating detailed and thoughtful questions based on workout plans and evaluating their quality using the G-Eval metric. It is designed to assist fitness enthusiasts, trainers, and developers working with structured workout plans in improving the clarity, relevance, and usability of their questions.

DeepEval examples using Gemini and ADK

Calibrated LLM-as-a-judge evaluation pipeline on AWS Bedrock Claude Sonnet 4.6 scores Claude Haiku 4.5 on AlpacaEval via DeepEval G-Eval with versioned rubrics, persisted chain-of-thought, and blind human calibration

Ši repozitorija skirta bakalauro darbui, kurio tikslas - tirti ir įgyvendinti lietuviškų pasirenkamojo atsakymo klausimų (MCQ) generavimo bei vertinimo procesą naudojant LLM.

DeepEval is an open-source LLM evaluation framework — built and maintained by Confident AI — for testing and benchmarking large language model applications. It is structured like Pytest but specialized for LLM systems, providing 40+ research-backed metrics (G-Eval, DAG, RAG metrics, agent metrics, multi-turn conversation metrics, multimodal…