EnterpriseOps-Gym: leaderboard
Stateful enterprise operations benchmark for LLM agents performing long-horizon planning, tool use, and policy-governed workflows.
Metric: Task Success Rate (imported). Source: enterpriseops-gym.github.io. Source: benchmarklist.com. Saturation forecast: Around May 2027. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 44.6 | #63 |
| 2 | Claude Sonnet 4.6 | 40.4 | #90 |
| 3 | Claude Opus 4.5 | 37 | #83 |
| 4 | Gemini 3.1 Pro (Preview) | 36.6 | #58 |
| 5 | Gemini 3 Flash | 31.7 | #99 |
| 6 | GPT-5.2 (High) | 31.3 | #110 (GPT-5.2) |
| 7 | Claude Sonnet 4.5 | 30.5 | #142 |
| 8 | GPT-5 | 29.2 | #98 |
| 9 | Gemini 3 Pro | 27.4 | #80 |
| 10 | Kimi K2.5 (Thinking) | 26.2 | #144 (Kimi K2.5) |
| 11 | DeepSeek V3.2 (High) | 23.8 | #205 (DeepSeek V3.2) |
| 12 | MiniMax-M2.7 | 23 | #258 |
| 13 | GPT-OSS-120B (High) | 23 | #341 (GPT-OSS-120B) |
| 14 | GLM-5 | 22.2 | #141 |
| 15 | GPT-5 Mini | 20.6 | #186 |
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 · How It Works · Data refreshed daily, snapshot 2026-10-20.