{"slug":"orchestra-research-evaluating-cosmos-policy","source_name":"orchestra-research/evaluating-cosmos-policy","name":"Orchestra Research/Evaluating Cosmos Policy","description":"Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.","version":1,"lift":{"pass_rate_delta_pts":80,"pass_rate_pct":100,"total_cases":25,"passed_cases":25,"tokens_delta_pct":142.9,"turns_delta_pct":0,"verdict":"pass","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-12T13:33:20.597138+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":80,"with_pass_pct":100,"without_pass_pct":20,"tokens_delta_pct":142.9,"turns_delta_pct":0,"total_cases":25,"cases_aggregated":23,"verdict":"pass","never_hurt":true,"completed_at":"2026-08-12T13:33:20.597138+00:00","run_id":"e910d8b3-ae6d-4e64-9998-aff085ffd653","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"cab669c3aa44d20416887702d57c5c2398f0fe929c832089124d967b94fd3df1","raw_url":"https://app.decimal.ai/s/orchestra-research-evaluating-cosmos-policy/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/orchestra-research-evaluating-cosmos-policy"}