{"type":"analysis","id":"analysis:research-gemini-4-argon-tops-vals-new-harvey-legal-board-but-it-already-beat-muse-spark","slug":"research-gemini-4-argon-tops-vals-new-harvey-legal-board-but-it-already-beat-muse-spark","title":"Gemini 4 Argon tops Vals' new Harvey legal board, but it already beat Muse Spark Open on v1","description":"On the HLAB-Vals-1.1 board, Muse Spark 1.2 is no longer #1 because it isn't listed, not because it lost a rerun. Scores rose across the board under a changed holdout set, harness and scoring, so v1 and v1.1 numbers can't be compared.","published_at":"2026-11-09T07:00:00.000Z","updated_at":"2026-11-09T07:00:00.000Z","record_date":"2026-11-09","topics":["gemini","research"],"source_urls":["https://www.vals.ai/benchmarks/hlab-v1","https://www.vals.ai/benchmarks/hlab","https://github.com/harveyai/harvey-labs/pull/76","https://www.mercor.com/apex/partner-benchmarks/harvey-lab-leaderboard/","https://artificialanalysis.ai/evaluations/harvey-lab-aa","https://www.harvey.ai/blog/introducing-harveys-legal-agent-benchmark"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-gemini-4-argon-tops-vals-new-harvey-legal-board-but-it-already-beat-muse-spark/","markdown":"https://newruntime.com/analysis/research-gemini-4-argon-tops-vals-new-harvey-legal-board-but-it-already-beat-muse-spark.md","json":"https://newruntime.com/analysis/research-gemini-4-argon-tops-vals-new-harvey-legal-board-but-it-already-beat-muse-spark.json"},"author":{"role":"author","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"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:aebdc47d-4b75-4669-a48f-3bf564039869","authorial_article_id":"aebdc47d-4b75-4669-a48f-3bf564039869"},"next_reads":[{"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":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}