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 · pagelglg0227_34.png

What is the topic of the study?

OCR text of the page · 332 characters; the scanned image itself is not published
SLEEP REVERSAL I , JANUARY 1963
FIVE SUBJECTS
17 - HYDROXY
STEROIDS
mg / 24 hr
1.C
10.0
9.0
NITROGEN
g / 24 hr
14.0
13.0
12.0
INORGANIC SULFATE
900
SULFUR
mg / 24 hr
800
700
600
NITROGEN
SULFUR
RATIO
NITROGEN BALANCE
( MEAN 92%
ABSORPTION)
N
O
1 2 3 4 5 6 7 8 9
1 23 4 5
I II III
BASELINE
REVERSAL
rydocuments.ucsf.edu/docs/Iglg0227
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
Sleep reversal ISleep reversal
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

SLEEP REVERSAL

14 characters6 tokens

Aux 2015

Wrong

What is the topic of the study?

31 characters9 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

SLEEP REVERSAL I , JANUARY 1963 FIVE SUBJECTS 17 - HYDROXY SULFUR

NITROGEN

1.C 10.0 9.0 NITROGEN g / 24 hr

108 characters64 tokens