EnterpriseOps-Gym-AA - ITSM: leaderboard
Artificial Analysis's implementation of ServiceNow's EnterpriseOps-Gym restricted to the IT service management (ITSM) domain: stateful, multi-step enterprise workflows completed through live tool use and graded on the final database state, with no partial credit. Task success rate, 0-100 (%); higher is better.
Metric: Task Success (%). Source: artificialanalysis.ai. Saturation forecast: Around 2029. 50 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.7 Flash (Medium) | 50.28 | #24 (Gemini 3.7 Flash) |
| 2 | Gemini 3.5 Flash (High) | 47.33 | #66 (Gemini 3.5 Flash) |
| 3 | Grok 4.6 (High) | 44.2 | #29 (Grok 4.6) |
| 4 | Qwen3.8 2.4T A95B | 44.2 | #59 |
| 5 | DeepSeek V4 Pro (0813) (Max) | 43.65 | #58 (DeepSeek V4 Pro (0813)) |
| 6 | Muse Spark 1.2 (xHigh) | 43.65 | #69 (Muse Spark 1.2) |
| 7 | GLM-5.3 (Max) | 43.09 | #44 (GLM-5.3) |
| 8 | Qwen 3.8 Max (0902) | 41.99 | #36 |
| 9 | Claude Opus 5 (Max) | 41.44 | #16 (Claude Opus 5) |
| 10 | Step 5 Preview | 41.44 | #53 |
| 11 | GPT-5.5 (xHigh) | 40.88 | #33 (GPT-5.5) |
| 12 | Kimi K3 (Max) | 39.41 | #35 (Kimi K3) |
| 13 | GLM-5.3 Flash | 38.12 | #77 |
| 14 | GLM-5.2 (Max) | 37.94 | #80 (GLM-5.2) |
| 15 | Qwen 3.8 27B (xHigh) | 37.57 | #123 (Qwen 3.8 27B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=enterpriseops-gym-aa-itsm · How It Works · Data refreshed daily, snapshot 2026-11-05.