{"type":"post","id":"four-new-benchmark-reviews-we-graded-one-as-d411d1","slug":"four-new-benchmark-reviews-we-graded-one-as-d411d1","title":"Four new benchmark reviews. We graded one as Verified, and three as Flawed.","description":"Epoch AI announced new reviews in its AI benchmark registry.","retrieval_nugget":"Epoch AI announced new reviews in its AI benchmark registry.","published_at":"2026-10-24","updated_at":"2026-10-24","record_date":"2026-10-24","date_kind":"published_at","topics":["evals","verification"],"entities":["Epoch AI"],"related_patterns":["ai-engineering-evaluations-are-splitting-into-task-specific"],"novelty_label":"new_fact","what_changed":"Epoch’s benchmark registry now reports four new benchmark reviews: one verified and three flawed.","prior_refs":["memory:0400603e-a93a-8583-a8ee-e0344084867d"],"source_url":"https://epoch.ai/benchmarks/search?reviewed=verified&reviewed=flawed&reviewed=not-enough-info","source_urls":["https://epoch.ai/benchmarks/search?reviewed=verified&reviewed=flawed&reviewed=not-enough-info"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:four-new-benchmark-reviews-we-graded-one-as-d411d1","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/four-new-benchmark-reviews-we-graded-one-as-d411d1/","markdown":"https://newruntime.com/posts/four-new-benchmark-reviews-we-graded-one-as-d411d1.md","json":"https://newruntime.com/posts/four-new-benchmark-reviews-we-graded-one-as-d411d1.json"},"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":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}