EnterpriseOps-Gym-AA - Teams: leaderboard
Artificial Analysis's implementation of ServiceNow's EnterpriseOps-Gym restricted to the Teams 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 | Muse Spark 1.2 (xHigh) | 51 | #69 (Muse Spark 1.2) |
| 2 | Gemini 3.7 Flash (Medium) | 51 | #24 (Gemini 3.7 Flash) |
| 3 | Kimi K3 (Max) | 49.67 | #35 (Kimi K3) |
| 4 | Step 5 Preview | 49 | #53 |
| 5 | Claude Sonnet 5 (Max) | 49 | #65 (Claude Sonnet 5) |
| 6 | Gemini 3.5 Flash (High) | 48.67 | #66 (Gemini 3.5 Flash) |
| 7 | Gemini 3.5 Flash Lite | 48 | #174 |
| 8 | DeepSeek V4 Pro (0813) (Max) | 48 | #58 (DeepSeek V4 Pro (0813)) |
| 9 | Grok 4.6 (High) | 48 | #29 (Grok 4.6) |
| 10 | Claude Sonnet 5 (xHigh) | 48 | #65 (Claude Sonnet 5) |
| 11 | Qwen 3.7 Max | 47.33 | #85 |
| 12 | GLM-5.2 (Max) | 47.33 | #80 (GLM-5.2) |
| 13 | Grok 4.5 (High) | 47 | #54 (Grok 4.5) |
| 14 | Qwen3.8 2.4T A95B | 47 | #59 |
| 15 | Claude Opus 5 (Max) | 46.67 | #16 (Claude Opus 5) |
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-teams · How It Works · Data refreshed daily, snapshot 2026-11-05.