EnterpriseOps-Gym-AA - Email: leaderboard
Artificial Analysis's implementation of ServiceNow's EnterpriseOps-Gym restricted to the Email 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 | Step 5 Preview | 70.19 | #53 |
| 2 | Qwen 3.7 Max | 69.87 | #85 |
| 3 | Kimi K3 (Max) | 68.59 | #35 (Kimi K3) |
| 4 | DeepSeek V4 Pro (0813) (Max) | 68.27 | #58 (DeepSeek V4 Pro (0813)) |
| 5 | Qwen 3.8 27B (xHigh) | 67.31 | #123 (Qwen 3.8 27B) |
| 6 | Gemini 3.7 Flash (Medium) | 67.31 | #24 (Gemini 3.7 Flash) |
| 7 | Muse Spark 1.2 (xHigh) | 66.35 | #69 (Muse Spark 1.2) |
| 8 | Qwen 3.8 Max (0902) | 66.35 | #36 |
| 9 | Gemini 3.5 Flash (High) | 66.03 | #66 (Gemini 3.5 Flash) |
| 10 | Claude Sonnet 5 (Max) | 65.38 | #65 (Claude Sonnet 5) |
| 11 | Mistral Medium 3.5 | 64.1 | #375 |
| 12 | Gemini 3.1 Pro (Preview) | 63.78 | #64 |
| 13 | Claude Sonnet 5 (xHigh) | 63.78 | #65 (Claude Sonnet 5) |
| 14 | Qwen 3.7 Plus | 62.5 | #98 |
| 15 | Inkling (xHigh) | 62.5 | #144 (Inkling) |
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-email · How It Works · Data refreshed daily, snapshot 2026-11-05.