Inference
OfficeQA Pro authors

OfficeQA Pro

A benchmark for grounded reasoning over office-style documents, spreadsheets, charts, and business artifacts.

ModelsModels with a result.12
Top resultBest result on this test.67.7%Claude Opus 5.5
Top-3 spreadPoints from first to third.1.5 pts
YearYear of release.2026

Result and price

020406080100$0.3$1$3$10$30$100RESULTOUTPUT PRICE PER 1M TOKENS · LOG SCALE

Results

12 results
#ModelResultThe score from the source.
01Claude Opus 5.567.7%
02Claude Opus 566.9%
03Claude Opus 4.866.2%
03Hy4 preview66.2%
05Kimi K363.3%
06GLM-5.3-Flash62.4%
07Step 5 Preview60.3%
08Claude Fable 557.9%
09GPT-5.554.1%
10GPT-5.453.2%
11MiniMax M345.1%
12Claude Opus 4.7 (Adaptive)43.6%