OccuBench - Commerce & Consumer: 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 Commerce & Consumer tasks in the clean environment, in percent; higher is better.
Metric: Completion rate (%) on the Commerce & Consumer 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: Not forecast. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3.5 Plus | Thinking | 81 | #242 |
| 2 | Gemini 3.1 Pro (Preview) | 75 | #99 | |
| 3 | Claude Sonnet 4.5 | Thinking | 69 | #261 |
| 4 | DeepSeek V3.2 | Thinking | 67 | #419 |
| 5 | GPT-5.2 | High | 67 | #185 |
| 6 | GLM-5 | Thinking | 67 | #269 |
| 7 | Qwen 3.5 Flash | Thinking | 67 | #441 |
| 8 | Claude Sonnet 4.6 | Thinking | 64 | #173 |
| 9 | Claude Sonnet 4 | Thinking | 61 | #410 |
| 10 | Gemini 3.1 Flash Lite | Thinking | 58 | #371 |
| 11 | MiniMax-M2.7 | 56 | #539 | |
| 12 | Kimi K2.5 | Thinking | 56 | #266 |
| 13 | Claude Opus 4.5 | Thinking | 56 | #160 |
| 14 | Claude Opus 4.6 | High | 53 | #113 |
| 15 | Claude Opus 4 | Thinking | 50 | #326 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=occubench-commerce-consumer · How It Works · Data refreshed daily, snapshot 2026-11-21.