EnterpriseOps-Gym-AA - Hybrid: leaderboard
Artificial Analysis's implementation of ServiceNow's EnterpriseOps-Gym restricted to the Hybrid (multi-domain) 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: Not forecast. 50 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4 Pro (0813) (Max) | 45.75 | #58 (DeepSeek V4 Pro (0813)) |
| 2 | Gemini 3.5 Flash (High) | 44.66 | #66 (Gemini 3.5 Flash) |
| 3 | Qwen 3.7 Max | 43.57 | #85 |
| 4 | Muse Spark 1.2 (xHigh) | 42.48 | #69 (Muse Spark 1.2) |
| 5 | Gemini 3.7 Flash (Medium) | 42.48 | #24 (Gemini 3.7 Flash) |
| 6 | Qwen 3.7 Plus | 41.39 | #98 |
| 7 | Kimi K3 (Max) | 41.18 | #35 (Kimi K3) |
| 8 | Gemini 3.5 Flash Lite | 41.18 | #174 |
| 9 | Grok 4.6 (High) | 39.87 | #29 (Grok 4.6) |
| 10 | Step 5 Preview | 39.87 | #53 |
| 11 | Gemini 3.1 Pro (Preview) | 39.65 | #64 |
| 12 | Mistral Medium 3.5 | 39.43 | #375 |
| 13 | Qwen3.8 2.4T A95B | 39.22 | #59 |
| 14 | Qwen 3.8 27B (xHigh) | 38.56 | #123 (Qwen 3.8 27B) |
| 15 | Qwen 3.8 Max (0902) | 38.56 | #36 |
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-hybrid · How It Works · Data refreshed daily, snapshot 2026-11-05.