# EnterpriseOps-Gym (provider runs) (EnterpriseOps-Gym)

> ServiceNow benchmark of stateful planning and tool use across simulated enterprise systems, as run by model providers.

Canonical page: https://benchlm.ai/benchmarks/enterpriseopsgym

- Category: [Agentic](/agentic)
- Last updated: October 29, 2026

## About EnterpriseOps-Gym

- Year: 2026
- Tasks: Enterprise workflow tasks
- Format: Task success rate
- Difficulty: Stateful enterprise tool use
- Paper: [EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings](https://arxiv.org/abs/2603.13594)

Liquid AI reports it for LFM3-1.7B (October 27, 2026) with up to 50 turns per task. Provider runs stay apart from Artificial Analysis's independent AA EnterpriseOps-Gym row.

EnterpriseOps-Gym is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [LFM3-1.7B](/models/lfm3-1-7b) | LiquidAI | 28.20% |

## FAQ

### What does EnterpriseOps-Gym measure?

ServiceNow benchmark of stateful planning and tool use across simulated enterprise systems, as run by model providers.

### Which model scores highest on EnterpriseOps-Gym?

LFM3-1.7B by LiquidAI currently leads with a score of 28.20% on EnterpriseOps-Gym.

### How many models are evaluated on EnterpriseOps-Gym?

1 AI models have published results on EnterpriseOps-Gym in the BenchLM catalog.

### Does EnterpriseOps-Gym affect BenchLM's overall score?

Not directly. EnterpriseOps-Gym is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.