An evaluation toolkit for multimodal models covering text, image, video and audio tasks with a unified interface, used to benchmark vision-language prompting.
Source: Official GitHub repository. Last checked 2026-09-18. Spot an error? Tell us.
Nearby and similar
A library for building LLM applications that also auto-tunes them, optimizing prompt text and few-shot demonstrations against a training set. It aims to make prompt tuning as routine as model training.
An observability and evaluation platform that turns production traces into datasets and prompt improvements, marketed for teams running self-improving agents.
An open-source workspace where engineers and subject-matter experts iterate on prompts and agent configurations side by side, with versioning, evaluation runs and observability.
A companion LangChain package focused on scoring agent trajectories, comparing the sequence of tool calls an agent made against an expected path.
An open-source red-teaming kit that fuzzes LLM endpoints with adversarial prompt datasets and multimodal attacks, producing a report of which defences failed.
A cookbook of plug-and-play JSON style packs for image models, where copying a single JSON block applies a complete visual style.