EnterpriseOps-Gym

Measures: An agent plans and carries out multi-step tasks, where actions cannot be undone, in a containerized enterprise sandbox (164 database tables, 512 tools across 8 domains such as customer service, HR, IT, email and calendar), following policy and refusing infeasible tasks; scored as task success rate.

Maintainer: ServiceNow AI Research (with Mila / Université de Montréal); Artificial Analysis runs EnterpriseOps-Gym-AA
Introduced: 2026
Status: Active
Saturation: Headroom
Typical provenance: Independent
In scoring set: Yes

Paper Official leaderboard

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.