OfficeQA Pro — leaderboard
Databricks OfficeQA Pro benchmark for harder professional office question-answering tasks.
Metric: Correctness (%). Source: www-cdn.anthropic.com. Status: saturation imminent. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 | 57.9 |
| 2 | GPT-5.5 | 52.6 |
| 3 | Claude Opus 4.8 | 48.1 |
| 4 | Gemini 3.1 Pro (Preview) | 18.1 |
Interactive version: theaggregate.ai/benchmark?slug=officeqa-pro · How the rankings work · Data refreshed daily, snapshot 2026-07-22.