Sign in
Pending benchmarksTracking since Nov 2, 2026

Is Drex for Finance state of the art?Pending benchmarks.Announced Nov 2, 2026; no independent results yet.

Nace AI's multimodal decision model post-trained for sub-second financial decisions such as document extraction, credit risk, fraud and AML scoring, market signals and sanctions screening. Nace's chart labels it Drex Max Finance. Available on Nace Console.

Announced facts

The details so far

Lab
Nace.AI
Announced
Nov 2, 2026
API
Live
Open weights
Unknown · Not mentioned by Nace
Type
Multimodal decision model, post-trained for financial decisions
Chart name
Drex Max Finance (Nace's benchmark chart), scored separately from Drex Max v1.1 and Drex Max v1
Domains
Financial documents and filings; credit and lending; fraud and AML; markets and trading; insurtech and regtech (Nace's list)
Access
Nace Console (console.nace.ai), per Nace; no API model id in Nace's public docs as of Nov 2, 2026
Parameters
Not stated by Nace
Earlier models
Separate from Drex Max, Drex v1.5 and Drex v2.0

Tags marked unsure are not stated on the lab's own pages.

Next steps

What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

  • Publicly announced with a source
  • Usable by the public (API or weights)
  • Listed on an independent board we track
  • Enough results for a rank in a category
  • Holds across two snapshots (crowns only)
Self-reported

What the lab claims

Self-reported. Shown for context; not used in any verdict.

Lab claim: 85.7% accuracy across 3,361 decisions on 48 held-out finance benchmarks, against 70.9% for GPT-6 Luna and 77.7% for Drex Max v1.1.

Lab claim: 77.3 on Nace's Finance Index, 13.7 points above Jev 1.14 and 11.5 points above Drex Max v1.1.

Receipts

Sources

LABNace AI announcement on Xx.com/NaceAI/status/2117298824926703953 · Nov 2, 2026LABNace Consoleconsole.nace.ai

Tracking continues until an independent board lists it.