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 · pagepqxf0227_1.png

How much Densen got for ‘category number 5,Nutrition ’?

OCR text of the page · 481 characters; the scanned image itself is not published
TEST ITEM ASSIGNMENTS
1957
Sheet No.
Date
CATEGORY
PHAIR
SHANIC DENSEN
Brown
BOUDOT
FLEMING
767 AL
BIOMETRICS
10
2
20
PUBLIC HEALTH
2
ADANNISTRATION
MATERNAL AND
CHILD HEALTH
10
MENTAL
HYGIENE
25
3 NUTRITION
ENVIORNMENTAL
SANITATION
26
JO CAMECONOMIC
ASPECTS MED CARE
26
REHABILITATION
PHYSICAL MED.
27
OCCUPATIONAL
HEALTH
22
10
EPIDEMIOLOGY
10
32
CHRONIC ILLNESS
& DEQ DISEASES
27
ACCIDENT
12
14
VITAL
STATISTICS
57
337
Source: https://www.industrydocuments.ucsf.edu/docs/pqxf0227
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
2
Models
4 of 4 columns · click a model to add or remove it

Ours

Partial · ANLS 0.50

26

2 characters3 tokens

Aux 2015

Wrong

TEST ITEM ASSIGNMENTS 1957 Sheet No. Date CATEGORY PHAIR SHANIC DENSEN Brown BOUDOT FLEMING 767 AL BIOMETRICS 10 2 20 PUBLIC HEALTH 2 ADANNISTRATION

149 characters64 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

OCTOBER OCTOBER OCTOBER OCTOBER OCTOBER OCTOBER OCTOBER OCTOBER OCTOBER OCTOBER OCTOBER OCTOBER OCTOBER

103 characters64 tokens