{"type":"post","id":"cognition-launched-frontiercode-2-0-a-coding-benchmark-c6b49a","slug":"cognition-launched-frontiercode-2-0-a-coding-benchmark-c6b49a","title":"Cognition launched FrontierCode 2.0 , a coding benchmark testing judgment under underspecified prompts","description":"Cognition has launched FrontierCode 2.0, a coding-agent benchmark designed to test engineering judgment when prompts leave important requirements unstated.","retrieval_nugget":"Cognition has launched FrontierCode 2.0, a coding-agent benchmark designed to test engineering judgment when prompts leave important requirements unstated. For teams building with AI, the release matters because it shifts evaluation closer to whether an agent’s change is actually mergeable, not merely whether it can satisfy a detailed task and a test suite.","published_at":"2026-10-27","updated_at":"2026-10-27","record_date":"2026-10-27","date_kind":"published_at","topics":["claude"],"entities":["Cognition","FrontierCode 2.0","FrontierCode 1.1","Devin","Claude Opus 5.5","GPT-6 Astra"],"related_patterns":["goal-scoped-loops-replace-manual-continuation","verification-bandwidth-is-the-scarce-resource"],"novelty_label":"new_fact","what_changed":"Cognition launched FrontierCode 2.0, expanding benchmark coverage and task scope and adding stricter mergeability criteria; it also reports updated model scores and cost comparisons.","prior_refs":["memory:1f800e00-04be-897e-af57-fe07de272b5a","memory:cfb3d1a9-d64d-8d46-a897-2318a354b470","memory:968435b2-9c0d-8e12-a305-adc894412425"],"source_url":"https://cognition.com/blog/frontier-code-2.0","source_urls":["https://cognition.com/blog/frontier-code-2.0"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:cognition-launched-frontiercode-2-0-a-coding-benchmark-c6b49a","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/cognition-launched-frontiercode-2-0-a-coding-benchmark-c6b49a/","markdown":"https://newruntime.com/posts/cognition-launched-frontiercode-2-0-a-coding-benchmark-c6b49a.md","json":"https://newruntime.com/posts/cognition-launched-frontiercode-2-0-a-coding-benchmark-c6b49a.json"},"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":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}