EnterpriseOps-Gym-AA - HR: leaderboard
Metric: Task Success (%). Source: artificialanalysis.ai. 48 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.6 (High) | 45.65 |
| 2 | Gemini 3.7 Flash (Medium) | 44.02 |
| 3 | Gemini 3.5 Flash (High) | 42.39 |
| 4 | Qwen3.8 2.4T A95B | 42.39 |
| 5 | GPT-5.5 (xHigh) | 41.3 |
| 6 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 40.76 |
| 7 | GLM-5.3 (Max) | 40.22 |
| 8 | GPT-5.5 (Medium) | 38.77 |
| 9 | Muse Spark 1.2 (xHigh) | 37.5 |
| 10 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 36.96 |
| 11 | Qwen 3.8 27B (xHigh) | 36.41 |
| 12 | Kimi K3 (Max) | 35.69 |
| 13 | Qwen 3.7 Max | 35.33 |
| 14 | Inkling Small | 35.33 |
| 15 | GLM-5.3 Flash | 34.78 |
Interactive version: theaggregate.ai/benchmark?slug=enterpriseops-gym-aa-hr · How It Works · Data refreshed daily, snapshot 2026-09-19.