The big labs approach Excel like any other code RL problem, not a financial one
@dealglassinc and @acephalt benchmarked Tetra, Opus 4.7, and GPT-5.5 for long-horizon financial modeling and found severe auditability gaps with the openpyxl/Python strategy
https://t.co/0lMckjjIsE
i quit my quant job at SIG to build @DealGlassInc
we just topped SpreadsheetBench Verified, mogging Opus 4.6, GPT-5.4, and Shortcut.
generic spreadsheet agents optimize for speed at the expense of quality. we built Tetra to underwrite billions.