EntCollabBench - Workflow: leaderboard
Task success in percent on 200 operational workflow tasks (160 single-step, 40 multi-step) carried out by role-specialized LLM agents for 11 enterprise roles that work behind permission-controlled ITSM, HR, CSM, Gitea and document services and delegate to each other (EntCollabBench, 2026), judged from execution traces and service-state changes. Higher is better.
Metric: Task success (%) on the 200 operational workflow tasks (160 single-step and 40 multi-step), judged from execution traces and service-state diffs, role-specialized LLM agents (11 enterprise roles behind permission-controlled ITSM, HR, CSM, Gitea and document services) delegate over HTTP, temperature 0, three-judge majority vote; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4 Pro | 59 | #201 |
| 2 | DeepSeek V4 Flash | 51 | #273 |
| 3 | Claude Sonnet 4.6 | 44 | #179 |
| 4 | Gemini 3.1 Pro (Preview) | 42.5 | #102 |
| 5 | GPT-5.4 | 33.5 | #138 |
| 6 | Qwen 3.5 122B A10B | 27.5 | #350 |
| 7 | Qwen 3.5 35B A3B | 25 | #494 |
| 8 | MiMo-V2-Flash | 21.5 | #691 |
| 9 | MiniMax-M2.7 | 18.5 | #539 |
| 10 | GPT-5 Mini | 17 | #373 |
| 11 | Gemini 3.1 Flash Lite (Preview) | 2 | #419 |
| 12 | Qwen 3.5 9B | 0 | #838 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=entcollabbench-workflow · How It Works · Data refreshed daily, snapshot 2026-11-22.