EnterpriseOps-Gym-AA - Calendar: leaderboard
Artificial Analysis's implementation of ServiceNow's EnterpriseOps-Gym restricted to the Calendar 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 2028. 50 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 (Max) | 51.28 | #16 (Claude Opus 5) |
| 2 | Qwen 3.8 Max (0902) | 50.96 | #36 |
| 3 | GPT-5.6 Luna (Max) | 49.04 | #79 (GPT-5.6 Luna) |
| 4 | Gemini 3.7 Flash (Medium) | 49.04 | #24 (Gemini 3.7 Flash) |
| 5 | GPT-5.6 Sol (Max) | 48.72 | #22 (GPT-5.6 Sol) |
| 6 | Qwen3.8 2.4T A95B | 48.08 | #59 |
| 7 | Claude Sonnet 5 (Max) | 48.08 | #65 (Claude Sonnet 5) |
| 8 | Muse Spark 1.2 (xHigh) | 47.12 | #69 (Muse Spark 1.2) |
| 9 | Kimi K3 (Max) | 46.79 | #35 (Kimi K3) |
| 10 | GPT-5.5 (xHigh) | 46.79 | #33 (GPT-5.5) |
| 11 | Claude Sonnet 5 (xHigh) | 46.79 | #65 (Claude Sonnet 5) |
| 12 | GLM-5.2 (Max) | 46.47 | #80 (GLM-5.2) |
| 13 | Claude Opus 4.8 (Max) | 46.15 | #39 (Claude Opus 4.8) |
| 14 | GPT-5.5 (Medium) | 45.51 | #33 (GPT-5.5) |
| 15 | Grok 4.6 (High) | 45.19 | #29 (Grok 4.6) |
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-calendar · How It Works · Data refreshed daily, snapshot 2026-11-05.