OfficeQA Pro: leaderboard
Databricks OfficeQA Pro benchmark for harder professional office question-answering tasks.
Metric: Correctness (%). Source: github.com. Source: www-cdn.anthropic.com. Saturation forecast: Around January 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 | 57.9 | #16 |
| 2 | GPT-5.5 | 52.6 | #31 |
| 3 | Claude Opus 4.8 | 48.1 | #37 |
| 4 | Gemini 3.1 Pro (Preview) | 18.1 | #58 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=officeqa-pro · How It Works · Data refreshed daily, snapshot 2026-10-20.