{"slug":"didhd-sagemaker-benchmark","source_name":"didhd/sagemaker-benchmark","name":"Didhd/Sagemaker Benchmark","description":"Run a managed performance benchmark against a deployed Amazon SageMaker AI endpoint using SageMaker AI inference benchmarking (part of optimized GenAI inference recommendations; NVIDIA AIPerf under the hood). Measures TTFT, ITL, request-latency percentiles, and throughput. Use when the user asks to benchmark / load-test / measure the performance of a live endpoint.","version":1,"lift":{"pass_rate_delta_pts":39.13,"pass_rate_pct":87,"total_cases":23,"passed_cases":20,"tokens_delta_pct":71.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-03T08:50:10.154486+00:00"},"skill_score":0.8696,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":39.13,"with_pass_pct":87,"without_pass_pct":47.8,"tokens_delta_pct":71.5,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":20,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-03T08:50:10.154486+00:00","run_id":"8e3c4c6a-dd9a-444e-8548-2f2aa371542a","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":"98e57bf7776a781adab0b0fa590cc72640e836863a788edfa74ec8538cf2601a","raw_url":"https://app.decimal.ai/s/didhd-sagemaker-benchmark/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/didhd-sagemaker-benchmark"}