{"type":"post","id":"artificial-analysis-launched-vials-aa-a-leaderboard-for-9086a6","slug":"artificial-analysis-launched-vials-aa-a-leaderboard-for-9086a6","title":"Artificial Analysis launched VIALS-AA, a leaderboard for scientific image reasoning across 161 tasks and 8 domains.","description":"Artificial Analysis has launched VIALS-AA, an independent evaluation of language models on 161 scientific-image interpretation tasks.","retrieval_nugget":"Artificial Analysis has launched VIALS-AA, an independent evaluation of language models on 161 scientific-image interpretation tasks. Its repeated trials and cost measures give teams a more specific view than general image benchmarks, while the results also underline how much specialized scientific interpretation remains distinct from describing ordinary pictures.","published_at":"2026-11-07","updated_at":"2026-11-07","record_date":"2026-11-07","date_kind":"published_at","topics":["claude","gemini"],"entities":["Artificial Analysis","Handshake AI","VIALS-AA","VIALS","Stirrup","Gemini 4 Carbon","GPT-6 Astra","Claude Opus 5.5"],"related_patterns":["model-answers-become-task-interfaces"],"novelty_label":"new_fact","what_changed":null,"prior_refs":[],"source_url":"https://artificialanalysis.ai/evaluations/vials-aa","source_urls":["https://artificialanalysis.ai/evaluations/vials-aa"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:artificial-analysis-launched-vials-aa-a-leaderboard-for-9086a6","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/artificial-analysis-launched-vials-aa-a-leaderboard-for-9086a6/","markdown":"https://newruntime.com/posts/artificial-analysis-launched-vials-aa-a-leaderboard-for-9086a6.md","json":"https://newruntime.com/posts/artificial-analysis-launched-vials-aa-a-leaderboard-for-9086a6.json"},"markdown_url":"https://newruntime.com/posts/artificial-analysis-launched-vials-aa-a-leaderboard-for-9086a6.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":"topic","path":"/topics/gemini/","url":"https://newruntime.com/topics/gemini/","title":"Gemini","reason":"Explore the gemini topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/gemini.md","json_url":"https://newruntime.com/topics/gemini.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"}]}