EnterpriseOps-Gym-AA - CSM: leaderboard
Metric: Task Success (%). Source: artificialanalysis.ai. 48 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 55.38 |
| 2 | Grok 4.6 (High) | 55.38 |
| 3 | GLM-5.3 (Max) | 54.84 |
| 4 | GPT-5.5 (xHigh) | 53.94 |
| 5 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 53.41 |
| 6 | Gemini 3.5 Flash (High) | 52.69 |
| 7 | Gemini 3.7 Flash (Medium) | 50.54 |
| 8 | GPT-5.5 (Medium) | 50.36 |
| 9 | GPT-5.6 Luna (Max) | 49.46 |
| 10 | Grok 4.5 (High) | 49.46 |
| 11 | GPT-5.6 Terra (Max) | 48.92 |
| 12 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | 48.92 |
| 13 | Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort) | 48.03 |
| 14 | GLM-5.3 Flash | 47.31 |
| 15 | Qwen3.8 2.4T A95B | 47.31 |
Interactive version: theaggregate.ai/benchmark?slug=enterpriseops-gym-aa-csm · How It Works · Data refreshed daily, snapshot 2026-09-19.