OccuBench - Business & Enterprise: leaderboard
OccuBench (2026) evaluates agents on 382 professional tool-use tasks from 100 occupational scenarios in 10 industries, against environments simulated by Gemini-3-Flash-Preview, each trajectory passed or failed by a rubric verifier; thinking mode on, high effort where configurable. This board is the completion rate on the Business & Enterprise tasks in the clean environment, in percent; higher is better.
Metric: Completion rate (%) on the Business & Enterprise industry's tasks in the clean environment (E0); 382 tool-use task instances from 100 professional scenarios, the environment simulated by Gemini-3-Flash-Preview and each trajectory passed or failed by a rubric verifier; thinking mode on, high reasoning effort where configurable; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.2 | High | 86 | #185 |
| 2 | DeepSeek V3.2 | Thinking | 78 | #419 |
| 3 | Claude Opus 4.6 | High | 78 | #113 |
| 4 | Claude Opus 4.5 | Thinking | 76 | #160 |
| 5 | GLM-5 | Thinking | 75 | #269 |
| 6 | Claude Opus 4 | Thinking | 75 | #326 |
| 7 | Gemini 3.1 Pro (Preview) | 73 | #99 | |
| 8 | Claude Sonnet 4.6 | Thinking | 71 | #173 |
| 9 | Claude Sonnet 4.5 | Thinking | 70 | #261 |
| 10 | Qwen 3.5 Plus | Thinking | 70 | #242 |
| 11 | Gemini 3.1 Flash Lite | Thinking | 70 | #371 |
| 12 | Claude Sonnet 4 | Thinking | 63 | #410 |
| 13 | Kimi K2.5 | Thinking | 62 | #266 |
| 14 | MiniMax-M2.7 | 60 | #539 | |
| 15 | Qwen 3.5 Flash | Thinking | 60 | #441 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=occubench-business-enterprise · How It Works · Data refreshed daily, snapshot 2026-11-21.