Output Explorer

Every prompt in the paper, and what each model wrote back.

Answer a question about a scanned page from its OCR text. Scored by exact match and ANLS against the accepted answers.

13 of 5,330 prompts

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagemzfm0227_1.png

How many sections are there in the questionnaire?

OCR text of the page · 1,510 characters; the scanned image itself is not published
OFFICIAL RECORD-IMMEDIATE RESPONSE REQUESTED
RECORD OF PHYSICIANS'
PROFESSIONAL ACTIVITIES
DIRECTORY OF PHYSICIANS
Please cross-out any prior information
which is not applicable.
AMERICAN MEDICAL ASSOCIATION
535 N. Dearborn Street
Chicago, Illinois 60610
Dear Doctor:
Recent information indicates there may have been a change in your
professional mailing address and/or professional status. Therefore,
will you please take a moment to assist us in correcting our records.
00401370137
Thank You
GROUP NAME
Instructions
ADDRESS
1. Please answer every question on the basis of your current activities.
CITY-STATE-ZIP
2. Indicate any changes. Information which you provided previously has been
printed in this form. Please complete unanswered sections and make dis-
crete changes where applicable.
3. Upon completion, return the questionnaire at your earliest possible con-
venience, using the preaddressed envelope.
Contents
The questionnaire is divided into three sections:
1. Professional Activities-the types of activities in which each physician spends
00401370137 00401370137
the most time during an average week.
WM JEFFERSON DARBY MD
I1. Specialization-the time physicians spend in their major fields of specialization.
VANDERBILT UNIV SCH MED
Ill. Present Employment Status- the number of hours per average week spent
under various practice arrangements, by type of practice organization
NASHVILLE TENN 37232
or employer.
ADDRESS
CITY-STATE-ZIP
Source: https://www.industrydocuments.ucsf edu/docs/mzfm0227
System prompt · identical for every setup
Answer the question using only the OCR text from a single document page. Return only the answer, with no explanation. Preserve the answer wording from the OCR text when possible.
Expected answer
threethree sections
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

three

5 characters2 tokens

Aux 2015

Wrong

1

1 characters2 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

Professional Activities-the types of activities in which each physician spends

00401370137 00401370137 the most time during an average week. WM JEFFERSON DARBY MD I1. Specialization-the time physicians spend in their major fields of specialization. VANDERBIL

262 characters64 tokens