EntCollabBench - Approval: leaderboard
Task success in percent on 100 policy approval tasks (80 single-step, 20 multi-step) decided 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), checked against deterministic policy adjudications. Higher is better.
Metric: Task success (%) on the 100 policy approval tasks (80 single-step and 20 multi-step), judged against deterministic policy adjudications, 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 | Claude Sonnet 4.6 | 70 | #173 |
| 2 | DeepSeek V4 Flash | 70 | #267 |
| 3 | DeepSeek V4 Pro | 68 | #196 |
| 4 | GPT-5 Mini | 62 | #364 |
| 5 | GPT-5.4 | 60 | #135 |
| 6 | Gemini 3.1 Pro (Preview) | 58 | #99 |
| 7 | Gemini 3.1 Flash Lite (Preview) | 46 | #417 |
| 8 | Qwen 3.5 122B A10B | 45 | #346 |
| 9 | Qwen 3.5 35B A3B | 43 | #492 |
| 10 | MiniMax-M2.7 | 37 | #539 |
| 11 | Qwen 3.5 9B | 23 | #828 |
| 12 | MiMo-V2-Flash | 7 | #684 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=entcollabbench-approval · How It Works · Data refreshed daily, snapshot 2026-11-21.