{"slug":"yogsoth-ai-evaluation-protocol-comparison","source_name":"yogsoth-ai/evaluation-protocol-comparison","name":"Yogsoth AI/Evaluation Protocol Comparison","description":"Compare implementation differences of same benchmark across papers","version":1,"lift":{"pass_rate_delta_pts":32,"pass_rate_pct":56,"total_cases":25,"passed_cases":14,"tokens_delta_pct":46.7,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-22T22:00:05.445262+00:00"},"skill_score":0.56,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":32,"with_pass_pct":56,"without_pass_pct":24,"tokens_delta_pct":46.7,"turns_delta_pct":0,"total_cases":25,"cases_aggregated":25,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-22T22:00:05.445262+00:00","run_id":"bfe2193f-628c-484c-8735-debeff710dd5","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":"4985b8654f2d347b8b901f10075623fcc218ec662e1e4fb6dd3e1203b18b5ffa","raw_url":"https://app.decimal.ai/s/yogsoth-ai-evaluation-protocol-comparison/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/yogsoth-ai-evaluation-protocol-comparison"}