DAYJOB: Tax A benchmark for AI tax agents

Blog
benchmarks
Off-the-Shelf
Training
experts
Products
Enterprise
Research
Careers
Contact

See you in Sydney

We’re going to NeurIPS from December 6–12, with three accepted workshop papers.

Let’s find time to meet.

Accepted papers
GDP.pdf: two-stage training and generalizationLong Context Foundation Models workshop
sudo L7 benchmarkInterpreting Agent Behavior workshop
DAYJOB benchmarkWorkshop on Agentic AI Benchmarks for Enterprise Tasks
What are you interested in?

By sending this request you agree to Surge AI’s Privacy Policy.

Thanks for reaching out, we’ll be in touch shortly.

Oops! Something went wrong while submitting the form.
© 2026 Surge AI
X
Linkedin
Cookie Settings
Cookie Policy
Privacy Policy
Terms of Service