{"type":"post","id":"earlier-evaluations-cover-adjacent-stages-of-scientific-work-679e76","slug":"earlier-evaluations-cover-adjacent-stages-of-scientific-work-679e76","title":"Earlier evaluations cover adjacent stages of scientific work.","description":"Benchling researchers introduce BenchBench-Protocol, a benchmark of 149 wet-lab protocol modification tasks drawn from changes scientists made during real experimental work.","retrieval_nugget":"Benchling researchers introduce BenchBench-Protocol, a benchmark of 149 wet-lab protocol modification tasks drawn from changes scientists made during real experimental work.","published_at":"2026-11-06","updated_at":"2026-11-06","record_date":"2026-11-06","date_kind":"published_at","topics":["claude"],"entities":["Benchling","BenchBench-Protocol","Claude Opus 5","GPT-5.6 Sol","GPT-5.6 Terra","Kimi K3","Exa"],"related_patterns":["scientific-agents-need-artifact-evidence"],"novelty_label":"new_fact","what_changed":"BenchBench-Protocol adds a benchmark based on 149 real-world wet-lab protocol modifications, extending scientific-agent evaluation to protocol reasoning and adaptation.","prior_refs":["https://newruntime.com/posts/new-benchmarks-cognition-s-frontiercode-2-0-merge-a78e19/"],"source_url":"https://arxiv.org/html/2608.23898v1","source_urls":["https://arxiv.org/html/2608.23898v1"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:earlier-evaluations-cover-adjacent-stages-of-scientific-work-679e76","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/earlier-evaluations-cover-adjacent-stages-of-scientific-work-679e76/","markdown":"https://newruntime.com/posts/earlier-evaluations-cover-adjacent-stages-of-scientific-work-679e76.md","json":"https://newruntime.com/posts/earlier-evaluations-cover-adjacent-stages-of-scientific-work-679e76.json"},"markdown_url":"https://newruntime.com/posts/earlier-evaluations-cover-adjacent-stages-of-scientific-work-679e76.md","next_reads":[{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.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"}]}