{"type":"post","id":"harvey-lab-aa-v1-1-benchmark-e10926","slug":"harvey-lab-aa-v1-1-benchmark-e10926","title":"Harvey LAB-AA v1.1 Benchmark","description":"Artificial Analysis has updated its implementation of Harvey’s Legal Agent Benchmark to v1.1, adding a source-document check that zeros a task’s headline score when the deliverable contains a material hallucination.","retrieval_nugget":"Artificial Analysis has updated its implementation of Harvey’s Legal Agent Benchmark to v1.1, adding a source-document check that zeros a task’s headline score when the deliverable contains a material hallucination. For teams evaluating legal agents, the change makes factual grounding part of success rather than a separate quality metric—and makes v1.1 scores incompatible with v1.0.","published_at":"2026-11-20","updated_at":"2026-11-20","record_date":"2026-11-20","date_kind":"published_at","topics":["evals","verification"],"entities":["Artificial Analysis","Harvey","Harvey LAB-AA v1.1","Stirrup","Astra for Law 6.2","GPT-6.2 Astra"],"related_patterns":["scientific-agents-need-artifact-evidence"],"novelty_label":"new_fact","what_changed":null,"prior_refs":[],"source_url":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","source_urls":["https://artificialanalysis.ai/evaluations/harvey-lab-aa"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:harvey-lab-aa-v1-1-benchmark-e10926","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/harvey-lab-aa-v1-1-benchmark-e10926/","markdown":"https://newruntime.com/posts/harvey-lab-aa-v1-1-benchmark-e10926.md","json":"https://newruntime.com/posts/harvey-lab-aa-v1-1-benchmark-e10926.json"},"markdown_url":"https://newruntime.com/posts/harvey-lab-aa-v1-1-benchmark-e10926.md","next_reads":[{"type":"topic","path":"/topics/evals/","url":"https://newruntime.com/topics/evals/","title":"Evals","reason":"Explore the evals topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/evals.md","json_url":"https://newruntime.com/topics/evals.json"},{"type":"topic","path":"/topics/verification/","url":"https://newruntime.com/topics/verification/","title":"Verification","reason":"Explore the verification topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/verification.md","json_url":"https://newruntime.com/topics/verification.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}
