{"id":1009,"slug":"worldbenchmark--intuitivephysics","name":"IntuitivePhysics","author":"worldbenchmark","description":"\n\t\n\t\t\n\t\n\t\n\t\tWorldBench\n\t\n\nWorldBench is a new benchmark designed to evaluate the physical understanding and prediction of modern world models and vision-language models. There are two components: \n\nVideo based: This is a benchmark designed to evaluate video-to-video world foundation models such as Cosmos. It consists of videos 132 frames long of 425 simulated scenes with RGB, Normals, Depth, Flow, and Segmentations.\nText based: This is a subset which adds text-based questions to 181 videos… See the full description on the dataset page: https://huggingface.co/datasets/worldbenchmark/IntuitivePhysics.","tags":"[\"Task_categories:visual-Question-Answering\",\"Task_categories:text-To-Video\",\"Language:en\",\"Size_categories:100K<n<1M\",\"Format:imagefolder\",\"Modality:image\"]","license":null,"framework":null,"parameters":null,"downloads":266888,"likes":6,"verified":0,"created_at":"2026-10-21 10:23:30","updated_at":"2026-10-21 10:23:30","source_url":"https://huggingface.co/datasets/worldbenchmark/IntuitivePhysics","source_platform":"huggingface","hf_repo_id":"worldbenchmark/IntuitivePhysics","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":1008,"model_id":1009,"version":"v1.0.0","manifest_hash":"10f104100c9f608ddb29d46bab198576a664b309406892e13a3a0d72ae0882da","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/worldbenchmark--intuitivephysics/v1.0.0.json","created_at":"2026-10-21 10:23:30"}],"files":[],"signatures":[{"id":1581,"version_id":1008,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"3f6a76c82da3aac23198d7c2315efb6da4ffec6b6e48940096ec5e6e2bd0303f","attestation_type":"registry","signed_at":"2026-10-21 10:23:30"}],"hndl":null}