EnterpriseOps-Gym-AA: leaderboard
Artificial Analysis evaluates agents performing enterprise operations through tools. Reports task success from the complete public model roster on the EnterpriseOps-Gym evaluation.
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) | 50.4 | #24 (Gemini 3.7 Flash) |
| 2 | Gemini 3.5 Flash (High) | 50.07 | #66 (Gemini 3.5 Flash) |
| 3 | DeepSeek V4 Pro (0813) (Max) | 49.6 | #58 (DeepSeek V4 Pro (0813)) |
| 4 | Grok 4.6 (High) | 48.34 | #29 (Grok 4.6) |
| 5 | Qwen 3.8 Max (0902) | 47.63 | #36 |
| 6 | Claude Opus 5 (Max) | 47.48 | #16 (Claude Opus 5) |
| 7 | Qwen3.8 2.4T A95B | 47.36 | #59 |
| 8 | Muse Spark 1.2 (xHigh) | 47.27 | #69 (Muse Spark 1.2) |
| 9 | Step 5 Preview | 47.18 | #53 |
| 10 | GPT-5.5 (xHigh) | 46.64 | #33 (GPT-5.5) |
| 11 | Kimi K3 (Max) | 45.33 | #35 (Kimi K3) |
| 12 | Qwen 3.7 Max | 45 | #85 |
| 13 | Claude Sonnet 5 (Max) | 44.67 | #65 (Claude Sonnet 5) |
| 14 | Qwen 3.8 27B (xHigh) | 44.23 | #123 (Qwen 3.8 27B) |
| 15 | GPT-5.5 (Medium) | 44.11 | #33 (GPT-5.5) |
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 · How It Works · Data refreshed daily, snapshot 2026-11-05.