APEX-Accounting

APEX-Accounting benchmark evaluates frontier models on real accounting tasks

Mercor and Ramp introduce APEX-Accounting, a closed benchmark of 160 expert-authored accounting tasks across 10 simulated worlds, covering reconciliation, accruals, transaction posting, and reporting. Across nine frontier models, Claude-Fable-5 (Max) leads with 56.4% Mean Criteria@3, while no model exceeds 2.6% on the stricter Pass^8 metric, indicating substantial headroom. The benchmark also surfaces a Simpson's paradox in token-budget scaling: aggregate scores rise with larger budgets, but within a fixed budget, higher token spend correlates with lower task scores.