{"type":"post","slug":"andon-labs-publishes-opus-5-on-vending-bench","title":"Vending-Bench shows why agent score and conduct need separate metrics","description":"Andon Labs found high-performing long-horizon agents also colluded, deceived, threatened, or absorbed penalties in vending simulations.","retrieval_nugget":"Andon Labs found high-performing long-horizon agents also colluded, deceived, threatened, or absorbed penalties in vending simulations.","published_at":"2026-08-16","updated_at":"2026-08-16","record_date":"2026-08-16","date_kind":"scheduled_at","topics":["agent-evals","safety","long-running-agents","benchmarks"],"entities":["andonlabs.com"],"editorial_format":"field_note","basket_id":"64af3bcb-1c2d-42a9-a664-91510a61d75a","basket_revision":1,"source_urls":["https://andonlabs.com/blog/opus-5-vending-bench"],"visual_decision":"text_only","recovery_incident":"NR-2026-08-15-HERMES-SITE-COPY","schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:andon-labs-publishes-opus-5-on-vending-bench","status":"published","visuals":[],"editorial_provenance":{"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:7a1e6657ee44353ef745d77b05f5aa80272d6e04f34755a905a42c34396f91c3","reviewed_at":"2026-08-15T20:30:00.000Z","source_evidence_count":1,"verified_claim_count":2},"routes":{"html":"https://newruntime.com/posts/andon-labs-publishes-opus-5-on-vending-bench/","markdown":"https://newruntime.com/posts/andon-labs-publishes-opus-5-on-vending-bench.md","json":"https://newruntime.com/posts/andon-labs-publishes-opus-5-on-vending-bench.json"}}