Provides 2,000 hours of synchronized, high‑fidelity robot‑free bimanual manipulation demonstrations with multi‑view video, calibrated end‑effector trajectories, gripper states, and language annotations. Curated from a 20,000+ hour corpus; features 6 camera views, ~3 mm pose accuracy, <40 µs cross‑sensor sync, and LeRobot v3‑style Parquet+MP4 export under CC BY 4.0.
[next-mdx-remote-client] error compiling MDX: Unexpected character `4` (U+0034) before name, expected a character that can start a name, such as a letter, `$`, or `_` More information: https://mdxjs.com/docs/troubleshooting-mdx
Evaluates multimodal context learning across grounding, new information application, and knowledge acquisition using a 3,443-instance benchmark spanning science, finance, long documents, spatial reasoning, and web VQA; finds current multimodal models perform poorly (best score 0.2847) and analyzes failure modes.
A collection of biology-focused 'mystery' tasks for benchmarking model performance on biomedical reasoning, evidence synthesis, and problem solving; curated by Anthropic and hosted on Hugging Face, designed for granular evaluation of scientific decision-making.
A small image-folder dataset for multimodal/vision model safety benchmarking, containing under 1,000 curated images with annotations to exercise safety-related model behaviours; licensed CC BY 4.0 and hosted on HuggingFace.
