Which AI model scores highest on OfficeQA Pro?

Claude Fable 5.1 by Anthropic holds the best OfficeQA Pro (extracted text) result among tracked models, at 69% (released Sep 1 2026). Higher scores are better on this benchmark.

What are the top 5 models on OfficeQA Pro?

1. Claude Fable 5.1 (Anthropic) — 69%; 2. Claude Opus 5.5 (Anthropic) — 67.7%; 3. Claude Mythos 5 (Anthropic) — 67.1%; 4. Claude Opus 5 (Anthropic) — 66.9%; 5. Claude Opus 4.8 (Anthropic) — 66.2%.

How many models have a published OfficeQA Pro score?

9 tracked models have a published OfficeQA Pro (extracted text) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

Document Q&A

OfficeQA Proextracted text

answering the 133 Treasury document questions with extracted text and code execution available

OfficeQA Pro extracted text

Rankings

Higher is better

OfficeQA Pro — frequently asked questions

: answering the 133 Treasury document questions with extracted text and code execution available
: Claude Fable 5.1 by Anthropic holds the best OfficeQA Pro (extracted text) result among tracked models, at 69% (released Sep 1 2026). Higher scores are better on this benchmark.
: 1. Claude Fable 5.1 (Anthropic) — 69%; 2. Claude Opus 5.5 (Anthropic) — 67.7%; 3. Claude Mythos 5 (Anthropic) — 67.1%; 4. Claude Opus 5 (Anthropic) — 66.9%; 5. Claude Opus 4.8 (Anthropic) — 66.2%.
: 9 tracked models have a published OfficeQA Pro (extracted text) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.