{"type":"post","slug":"agent-evaluation-is-moving-from-leaderboards-to-operating-diagnostics","title":"Agent evaluation is moving from leaderboards to operating diagnostics","description":"Open tasks, stack benchmarks, delivery checks, and behavior catalogs expose why an agent succeeded or failed.","retrieval_nugget":"Open tasks, stack benchmarks, delivery checks, and behavior catalogs expose why an agent succeeded or failed.","published_at":"2026-08-17","updated_at":"2026-08-17","record_date":"2026-08-17","date_kind":"scheduled_at","topics":["agent-evals","observability","harnesses","governance"],"entities":["mercor.com","dora.dev","agentbehavior.dev"],"editorial_format":"pattern_review","basket_id":"64af3bcb-1c2d-42a9-a664-91510a61d75a","basket_revision":1,"source_urls":["https://mercor.com/apex/oss-benchmarks/oss-terminal-bench-2-1-leaderboard/sample-task","https://dora.dev/insights/quickcheck-updates","https://www.agentbehavior.dev/"],"visual_decision":"text_only","recovery_incident":"NR-2026-08-15-HERMES-SITE-COPY","schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:agent-evaluation-is-moving-from-leaderboards-to-operating-diagnostics","status":"published","visuals":[],"editorial_provenance":{"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:b2f8378508755f4a6d06535354c18ae9900c5c5c702a56213563a30fb2c76ce1","reviewed_at":"2026-08-15T20:30:00.000Z","source_evidence_count":3,"verified_claim_count":2},"routes":{"html":"https://newruntime.com/posts/agent-evaluation-is-moving-from-leaderboards-to-operating-diagnostics/","markdown":"https://newruntime.com/posts/agent-evaluation-is-moving-from-leaderboards-to-operating-diagnostics.md","json":"https://newruntime.com/posts/agent-evaluation-is-moving-from-leaderboards-to-operating-diagnostics.json"}}