Professional accounting
APEX-Accounting
Month-end accounting work across 10 business worlds: 160 tasks and 2,186 grading criteria.
About APEX-Accounting
What it measures
Mean criteria passed; task success and consistency across repeated attempts. Publisher reports task-level bootstrap intervals.
Scope & limitations
The 160-task leaderboard split is private. A separate public world is a sample, not the full benchmark. Licensed source access is required before full-suite execution.
Evaluation environment
Accounting applications, spreadsheets, documents and code; source-defined task rubrics and the published Loop Harness.