ai-evaluation-framework

☑️ A curated list of tools, methods & platforms for evaluating AI reliability in real applications

Comprehensive AI Model Evaluation Framework with advanced techniques including Temperature-Controlled Verdict Aggregation via Generalized Power Mean. Support for multiple LLM providers and 15+ evaluation metrics for RAG systems and AI agents.

Open-source AI model evaluation and benchmarking framework for LLMs (OpenAI, Ollama, Claude, Gemini)

Core engine behind Calibrate, a framework for evaluating AI agents: speech-to-text, text-to-speech, LLM evaluation, end-to-end simulations

A comprehensive, implementation-focused guide to evaluating Large Language Models, RAG systems, and Agentic AI in production environments.

Comprehensive AI Evaluation Framework with advanced techniques including Temperature-Controlled Verdict Aggregation via Generalized Power Mean. Support for multiple LLM providers and 15+ evaluation metrics for RAG systems and AI agents.

[NeurIPS 2025] AGI-Elo: How Far Are We From Mastering A Task?

Test and evaluate Large Language Models against prompt injections, jailbreaks, and adversarial attacks with a web-based interactive lab.

Deterministic runtime for agent evaluation

prompt-evaluator is an open-source toolkit for evaluating, testing, and comparing LLM prompts. It provides a GUI-driven workflow for running prompt tests, tracking token usage, visualizing results, and ensuring reliability across models like OpenAI, Claude, and Gemini.

Curated intelligence layer for generative and agentic AI, translating research into production systems | AditiKhare.com — AI Product Ecosystem

🤖 Evaluate AI systems effectively with our comprehensive guide to methods, tools, and frameworks for assessing Large Language Models and agents.

VerifyAI is a verification harness for testing, auditing, and evaluating responses from AI assistants and coding agents.

Frontend for Calibrate, a framework for evaluating AI agents: speech-to-text, text-to-speech, LLM evaluation, end-to-end simulations

A reference implementation for learning and building AI evaluation systems.

Pondera is a lightweight, YAML-first framework to evaluate AI models and agents with pluggable runners and an LLM-as-a-judge.

Multi-dimensional evaluation of AI responses using semantic alignment, conversational flow, and engagement metrics.

Sandbox platform for testing and evaluating autonomous agents

🔍 Run efficient evaluations for prompt and LLM regression testing with this lightweight, secret-free evaluation harness.

Backend for Calibrate, a framework for evaluating AI agents: speech-to-text, text-to-speech, LLM evaluation, end-to-end simulations