Gemini 4 Argon tops Vals AI Finance Agent v2 benchmark

A Japanese bank employee says Gemini 4 Argon ranks first on the 927-question Vals AI Finance Agent v2 benchmark covering EDGAR search, filings, financial calculations and stock analysis, and also praises its role-play dialogue.

かぶまる

@kabumaru555Archived 21 days agoOriginally posted 2026.10.14