EnterpriseOps-Gym — leaderboard
Stateful enterprise operations benchmark for LLM agents performing long-horizon planning, tool use, and policy-governed workflows.
Metric: Task Success Rate (self-reported). Source: benchmarklist.com. Status: saturation imminent. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 44.6 |
| 2 | Claude Sonnet 4.6 | 40.4 |
| 3 | Claude Opus 4.5 | 37 |
| 4 | Gemini 3.1 Pro (Preview) | 36.6 |
| 5 | Gemini 3 Flash (Preview) | 31.7 |
| 6 | GPT-5.2 (High) | 31.3 |
| 7 | Claude Sonnet 4.5 | 30.5 |
| 8 | GPT-5 | 29.2 |
| 9 | Nemotron 3 Super | 27.3 |
| 10 | Kimi K2.5 | 26.2 |
| 11 | DeepSeek V3.2 (High) | 23.8 |
| 12 | MiniMax-M2.7 | 23 |
| 13 | GPT-OSS-120B (High) | 23 |
| 14 | GLM-5 | 22.2 |
| 15 | GPT-5 Mini | 20.6 |
Interactive version: theaggregate.ai/benchmark?slug=enterpriseops-gym · How the rankings work · Data refreshed daily, snapshot 2026-07-22.