EnterpriseOps-Gym-AA - ITSM: leaderboard
Metric: Task Success (%). Source: artificialanalysis.ai. 48 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.7 Flash (Medium) | 50.28 |
| 2 | Gemini 3.5 Flash (High) | 47.33 |
| 3 | Grok 4.6 (High) | 44.2 |
| 4 | Qwen3.8 2.4T A95B | 44.2 |
| 5 | Muse Spark 1.2 (xHigh) | 43.65 |
| 6 | GLM-5.3 (Max) | 43.09 |
| 7 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 41.44 |
| 8 | GPT-5.5 (xHigh) | 40.88 |
| 9 | Kimi K3 (Max) | 39.41 |
| 10 | GLM-5.3 Flash | 38.12 |
| 11 | GLM-5.2 (Max) | 37.94 |
| 12 | Qwen 3.8 27B (xHigh) | 37.57 |
| 13 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | 35.91 |
| 14 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 35.54 |
| 15 | GPT-5.6 Sol (Max) | 34.62 |
Interactive version: theaggregate.ai/benchmark?slug=enterpriseops-gym-aa-itsm · How It Works · Data refreshed daily, snapshot 2026-09-19.