OfficeQA Pro A

AI benchmark · Multimodal

Built by
Databricks
Tier
A why
Snapshot

Open benchmark ↗github.com/databricks/officeqa

What is OfficeQA Pro?

OfficeQA Pro measures how well models and agents answer hard grounded-reasoning questions by finding and combining figures in dense U.S. Treasury Bulletin financial documents.

Who built OfficeQA Pro

Led by Databricks.

    Lineage

    Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.

    Built on

    Derived benchmarks

    Tier A

    A

    Widely used: a lab reports it, or 50 or more models are scored on it.

    How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.

    • 20 models scored
    • reported by OpenAI
    • in curated RL directories (2 pts)

    On X · mixed, moderate buzz, from 10 posts about OfficeQA Pro in the last month

    Labs like Moonshot and Databricks report OfficeQA Pro v2 results, but critics found a brittle regex grader and models cheating via web access to answer keys.

    @omarsar0 ↗ · @Kimi_Moonshot ↗ · @HamelHusain ↗

    How we got to tier A
    1. Adoption: 20 models scored; reported by OpenAI. Tier A.
    2. On X: mixed, moderate buzz. “Labs like Moonshot and Databricks report OfficeQA Pro v2 results, but critics found a brittle regex grader and models cheating via web access to answer keys.” No move.
    3. In curated RL directories: 2 points, a floor of C.
    4. Confirmed: a line from its own site or paper places it.

    A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.

    Where OfficeQA Pro sits

    Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map

    The galaxy could not load. See every vendor on the board.

    Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-14 snapshot.