Mercor built APEX-Accounting with Ramp to see if agents can handle a real company's books.

Public source

Publisher name

Public post

GPT-6 Astra passes more tasks on APEX-Accounting than any other model. 13.1% Pass@1 (#1) 60.0% mean score (#2) Pass@1 is the proportion of tasks that a model scores 100%…

Log in to read the full post

Company

Mercor

Organizing human intelligence to power the AI economy.

Industry
Software Development
Location
San Francisco, US
Company size
10,001+ employees

About Mercor

We find the best experts in every professional domain and put their knowledge to work training frontier models. Through APEX, we measure whether those models can actually perform economically valuable work. We're also bringing that expertise to enterprises: deploying custom AI agents, staffing teams with vetted domain experts, and helping organizations encode their own knowledge into AI systems.

See more

Latest activity

17 signals

Discover more

Similar public activity from other companies.

Customize signals for your business.

Know everything happening across the B2B world, and act on the company movements that matter to you.

© 2026 SeedOpsCompany intelligence.

SeedOps.