{"slug":"nvidia-rag-eval","source_name":"nvidia/rag-eval","name":"Nvidia/RAG Eval","description":"Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.","version":1,"lift":{"pass_rate_delta_pts":63.64,"pass_rate_pct":86.4,"total_cases":22,"passed_cases":19,"tokens_delta_pct":61.8,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-12T23:05:03.066818+00:00"},"skill_score":0.8636,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":63.64,"with_pass_pct":86.4,"without_pass_pct":22.7,"tokens_delta_pct":61.8,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-12T23:05:03.066818+00:00","run_id":"98404538-dcf7-487e-ad07-a6ecd3aec16d","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":"Apache-2.0","install_count":0,"manifest_hash":"c498d74723bb841617f16d97c1c0aec420ab117cfbe62f972897bbe3689271dc","raw_url":"https://app.decimal.ai/s/nvidia-rag-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/nvidia-rag-eval"}