Agentic benchmark
AA EnterpriseOps-Gym leaderboard
Artificial Analysis EnterpriseOps-Gym. Every model the catalog carries a published AA EnterpriseOps-Gym value for, ranked by that value.
An independently evaluated enterprise-operations benchmark from Artificial Analysis.
AA EnterpriseOps-Gym ranking
17 models with a published AA EnterpriseOps-Gym value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Task success rate |
|---|---|---|---|
| 1 |  Claude Fable 5 | Anthropic | 51.1 |
| 2 |  Gemini 3.5 Flash | 50.1 | |
| 3 |  DeepSeek V4 Pro 0813 | DeepSeek | 49.6 |
| 4 |  Grok 4.6 | xAI | 48.3 |
| 5 | Claude Opus 5 | Anthropic | 47.5 |
| 6 |  Muse Spark 1.2 | Meta | 47.3 |
| 7 |  GPT-5.5 | OpenAI | 46.6 |
| 8 |  Kimi K3 | Moonshot AI | 45.3 |
| 9 |  Qwen3.8-27B | Alibaba | 44.2 |
| 10 | GPT-5.6 Sol | OpenAI | 42.9 |
| 11 | Gemini 3.5 Flash-Lite | 42.3 | |
| 12 | GPT-5.6 Luna | OpenAI | 40.8 |
| 13 | GPT-5.6 Terra | OpenAI | 38.5 |
| 14 | TMInkling | Thinking Machines Lab | 38.0 |
| 15 |  GLM-5.3 | Z.AI | 36.4 |
| 16 | Muse Glimmer 30B | Meta | 34.7 |
| 17 |  Mistral Medium 3.5 128B | Mistral | 33.7 |
Evidence key: ObservedLast good
Rows are ordered by the value Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.