Skip to page content
SAVRN
Search Plan a project

Organization

MMOrgBench

MMOrgBench

Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers1

Compare the published evidence

This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Visual question answering.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Datasets

Dataset · Visual question answering

MMOrgBench

MMOrgBench

1,801 omni-view questions over 32 synthetic workplace projects. This is the portable evaluation corpus, not the original source-paper collection. PDF/PPT content is supplied as rendered page images; native Slack/Notion messages remain text. No OCR or generated image captions are supplied to readers. Pin a Hub commit SHA with revision=" " for reproducible experiments. The QA dataset contains question, answer, task, reviewed evidence, solution and annotationjson with the full review record. Gold and solution are evaluation Download all actual images and the corpus for evaluation: corpus/units.json has repository-relative image paths. Every image is included in media/ with a content-hash…

Publicly accessible