{"type":"post","id":"our-latest-batch-includes-4-new-reviews-1-b778bd","slug":"our-latest-batch-includes-4-new-reviews-1-b778bd","title":"Our latest batch includes 4 new reviews: 1 Verified and 3 Flawed.","description":"Epoch AI says its latest Benchmark Reviews batch adds four reviews with verdicts: one benchmark was rated Verified and three were rated Flawed.","retrieval_nugget":"Epoch AI says its latest Benchmark Reviews batch adds four reviews with verdicts: one benchmark was rated Verified and three were rated Flawed.","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","Benchmark Reviews"],"related_patterns":["ai-engineering-evaluations-are-splitting-into-task-specific"],"novelty_label":"new_fact","what_changed":"Epoch AI’s latest batch adds four benchmark reviews: one rated Verified and three Flawed.","prior_refs":["memory:0400603e-a93a-8583-a8ee-e0344084867d","memory:cd427634-b3e2-86e2-a42c-a08cf83d2391"],"source_url":"https://epoch.ai/data/benchmark-reviews-documentation/included-benchmarks","source_urls":["https://epoch.ai/data/benchmark-reviews-documentation/included-benchmarks"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:our-latest-batch-includes-4-new-reviews-1-b778bd","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/our-latest-batch-includes-4-new-reviews-1-b778bd/","markdown":"https://newruntime.com/posts/our-latest-batch-includes-4-new-reviews-1-b778bd.md","json":"https://newruntime.com/posts/our-latest-batch-includes-4-new-reviews-1-b778bd.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"}]}