{"slug":"aperivue-mllm-eval","source_name":"aperivue/mllm-eval","name":"Aperivue/Mllm Eval","description":"Design or audit a model-agnostic evaluation harness for an LLM or multimodal LLM on a clinical task (radiology report generation, visual question answering, clinical text extraction/classification) — the adjudicated reference standard, clinical-efficacy metrics (RadGraph-F1 / CheXbert-F1 beyond BLEU/ROUGE), faithfulness and hallucination, pretraining-contamination of public benchmarks, prompt-sensitivity and determinism, answer-matching, and a reader study — and gate the plan for those axes. Wor","version":3,"lift":{"pass_rate_delta_pts":47.83,"pass_rate_pct":95.7,"total_cases":23,"passed_cases":22,"tokens_delta_pct":33,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-10-10T19:50:22.423767+00:00"},"skill_score":0.9565000000000001,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":47.83,"with_pass_pct":95.7,"without_pass_pct":47.8,"tokens_delta_pct":33,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":true,"completed_at":"2026-10-10T19:50:22.423767+00:00","run_id":"5e04b9c0-a8f6-4831-b713-9da2d5379f99","latest_attempt":{"id":"5e04b9c0-a8f6-4831-b713-9da2d5379f99","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-10-10T19:50:22.423767+00:00","gate":null},"version_number":3,"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,"total_uses":0,"total_users":0,"manifest_hash":"72249604a3e8d49c9e4aad7abd6a6ab1a88766ba3e22311e922e4d3fb6e00784","install_name":"aperivue-mllm-eval","version_id":"f8b3850c-24b7-414b-9c5f-dfc5ed6d0a06","body_sha256":"72249604a3e8d49c9e4aad7abd6a6ab1a88766ba3e22311e922e4d3fb6e00784","render_hash":"e19a143c81fca0b8e3426d9964054a64ad920c2c230cd1b3c4c590d4a48bf1a8","raw_url":"https://app.decimal.ai/s/aperivue-mllm-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/aperivue-mllm-eval"}