Shypd.aiThe largest open index of AI toolsLiveBench is an open-source benchmark tool that evaluates large language models (LLMs) with a focus on contamination-free assessment. It provides a challenging set of tasks and objective ground-truth answers to accurately score models.
Trending
About
LiveBench is an open-source benchmark designed for evaluating large language models (LLMs) with a strong emphasis on preventing test set contamination. It achieves this by regularly releasing new questions based on recent datasets, arXiv papers, news articles, and IMDb synopses. The benchmark features 18 diverse tasks across 6 categories, each with verifiable, objective ground-truth answers, allowing for accurate and automatic scoring without relying on LLM judges. LiveBench supports evaluating models via OpenAI-compatible APIs, offers parallel evaluation options for efficiency, and provides tools for viewing results and error checking. It's an essential resource for researchers and engineers to assess and compare LLM performance reliably.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
.png&w=3840&q=75){kind=logo}
