ai-evaluation topic

Vivaria is METR's tool for running evaluations and conducting agent elicitation research.

METR

Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.

lechmazur

Benchmark evaluating LLMs on their ability to create and resist disinformation. Includes comprehensive testing across major models (Claude, GPT-4, Gemini, Llama, etc.) with standardized evaluation met...

lechmazur

Code scanner to check for issues in prompts and LLM calls

kereva-dev