Claude Opus 5.5 Is Now Available on Filot
Anthropic's Claude Opus 5.5 is now available on Filot. It builds more thorough financial models than Opus 5, in less time and at lower cost.
Claude Opus 5.5, the first model in Anthropic's Claude 5.5 family, is now available on Filot. Workspaces running Opus 5 move to Opus 5.5 automatically. Nothing else in your configuration changes.
In our own testing on financial modeling work, Opus 5.5 is a clear step up from Opus 5. It is diligent, thorough, and communicates more clearly.
The numbers point the same way. In a head-to-head test, both models built an Excel model to assess whether a proposed merger made sense at its price. Both reached the same conclusion. Opus 5.5's model was more thorough, while Opus 5's contained minor errors. Opus 5.5 completed the analysis in 63 minutes against 93, at half the cost.
It is also more careful with sources. In a separate test, research reports were checked figure by figure and quote by quote, and a single invented number failed the report. Opus 5.5 passed 16 of 18 attempts. Opus 5 passed none.
In Filot, that shows up where analysts spend their time. Buy-side teams get earnings updates turned around faster the morning a print lands. Research teams get initiations and model builds that are more complete on the first pass. Bankers get merger and LBO models ready for review sooner. Every figure still ties back to its source through Filot's audit trail, under the same validation controls as before.
"Opus 5.5 is a real step up from Opus 5 on the work our customers do every day. It builds more complete models, makes fewer errors and gets there faster. For an analyst, that means a better first draft, sooner." — Bjorn Birkelund, Co-Founder & CEO of Filot
Opus 5.5 runs under the same data handling as Opus 5, with no training on your data. Questions about the rollout for your organization go to your Filot contact.
More from Filot
See all →Fable 5.1 Is Now Available on Filot
Anthropic's newest frontier model is now available on Filot. It leads our internal evaluations on long-running financial modeling tasks, and discounted prompt cache reads make it cheaper to run than Fable 5.
Verifying AI Output Shouldn't Take Longer Than the Work Itself
AI only saves time if you can verify its work efficiently. Filot audits at two levels, deterministic validation checks and granular cell-by-cell traceability, so analysts review AI-generated models at the speed of reading, not the speed of searching.
Claude Sonnet 5 Is Now the Default on Filot
Anthropic's Claude Sonnet 5 is now the default model powering every Filot workflow — stronger reasoning, better tool use, and improved performance on long-running financial modeling tasks.