{"type":"post","id":"pws-decisions-a-benchmark-for-web-grounded-decisions-162380","slug":"pws-decisions-a-benchmark-for-web-grounded-decisions-162380","title":"PWS-Decisions: a benchmark for web-grounded decisions","description":"Parallel has open-sourced PWS-Decisions, a 300-question benchmark for questions whose answers depend on current information on the web.","retrieval_nugget":"Parallel has open-sourced PWS-Decisions, a 300-question benchmark for questions whose answers depend on current information on the web. Its results highlight a practical evaluation gap: systems that perform similarly on prompt-answerable tasks can diverge when they must ground a decision in live web evidence.","published_at":"2026-11-02","updated_at":"2026-11-02","record_date":"2026-11-02","date_kind":"published_at","topics":["agent-economics"],"entities":["Parallel","PWS-Decisions","Parallel Decisions API","OpenAI Decisions","Jev","JevBench"],"related_patterns":["agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"Parallel open-sources a 300-question live-web decision benchmark, reporting its Decisions API scores 1.5× the closest competitor.","prior_refs":["https://newruntime.com/posts/parallel-decisions-api-web-grounded-classification-dc4d7c/"],"source_url":"https://parallel.ai/blog/pws-decisions-benchmark","source_urls":["https://parallel.ai/blog/pws-decisions-benchmark"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:pws-decisions-a-benchmark-for-web-grounded-decisions-162380","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/pws-decisions-a-benchmark-for-web-grounded-decisions-162380/","markdown":"https://newruntime.com/posts/pws-decisions-a-benchmark-for-web-grounded-decisions-162380.md","json":"https://newruntime.com/posts/pws-decisions-a-benchmark-for-web-grounded-decisions-162380.json"},"markdown_url":"https://newruntime.com/posts/pws-decisions-a-benchmark-for-web-grounded-decisions-162380.md","next_reads":[{"type":"topic","path":"/topics/agent-economics/","url":"https://newruntime.com/topics/agent-economics/","title":"Agent Economics","reason":"Explore the agent-economics topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-economics.md","json_url":"https://newruntime.com/topics/agent-economics.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"}]}