{"slug":"dexforce-benchmark","source_name":"dexforce/benchmark","name":"Dexforce/Benchmark","description":"Write benchmark scripts for EmbodiChain modules following project conventions","version":4,"lift":{"pass_rate_delta_pts":60,"pass_rate_pct":92,"total_cases":25,"passed_cases":23,"tokens_delta_pct":138.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-03T19:19:05.255960+00:00"},"skill_score":0.92,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":60,"with_pass_pct":92,"without_pass_pct":32,"tokens_delta_pct":138.3,"turns_delta_pct":0,"total_cases":25,"cases_aggregated":24,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-03T19:19:05.255960+00:00","run_id":"aa0d1ae3-5131-411b-808f-d4726a686d64","latest_attempt":{"id":"aa0d1ae3-5131-411b-808f-d4726a686d64","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-09-03T19:19:05.255960+00:00","gate":null},"version_number":3,"is_latest_version":false,"gate":null},{"model":"gemini-3.8-flash","headline":false,"delta_pts":null,"with_pass_pct":null,"without_pass_pct":null,"tokens_delta_pct":96.2,"turns_delta_pct":0,"total_cases":24,"cases_aggregated":24,"verdict":"mixed","never_hurt":false,"completed_at":"2026-10-21T06:25:20.459304+00:00","run_id":"54955bd4-c9f2-4b80-9b72-a82207e01982","latest_attempt":{"id":"54955bd4-c9f2-4b80-9b72-a82207e01982","runner_model":"gemini-3.8-flash","overall_verdict":"mixed","completed_at":"2026-10-21T06:25:20.459304+00:00","gate":"not_comparable"},"version_number":4,"is_latest_version":true,"gate":"not_comparable"}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"3af119f498fb33227379f20c11e2cabbc6b0d10346594a565f5496b0593e29a4","install_name":"dexforce-benchmark","version_id":"7d17cee2-d176-405e-9edf-01d4ca7c6a03","body_sha256":"3af119f498fb33227379f20c11e2cabbc6b0d10346594a565f5496b0593e29a4","render_hash":"42520ef480e397c885cae7f30143e52e3fe80d58957c21ae246491f108ed8c1d","raw_url":"https://app.decimal.ai/s/dexforce-benchmark/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/dexforce-benchmark"}