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 · pagepyyc0227_66.png

What is the x-axis of first bar graph?

OCR text of the page · 795 characters; the scanned image itself is not published
TOTAL GROUP
MALNOURISHED
17-
DIARRHEA
CURRENT RECENT RECURRENT
TOTAL GROUP
40-
15-
WEIGHT
13-
MALNOURISHED
30-
11-
( MARASMUS,
PREKWASHIORKOR,
9 -
KWASHIOKOR )
Ka
prevalence
20-
7 -
TOTAL GROUP
100-
HEIGHT
MALNOURISHED
(MARASMUS,
AGE (mos)
0-5
6-11
12-17
18-23
24-29
30-35
36 +
95-
PREKWASHIORKOR,
40-
KWASHIORKOR)
RESPIRATORY
INFECTIONS
90-
30 -
85-
%
80-
prevalence
Cm
20-
75-
70-
10
65-
60-
NO.
MALNOURISH-
10
38
32
13
ED
AGE (mos)
0-5
6-11
12 - 17
18-23
24-29
30-35
36+
AGE (MOS)
0-5 6-11 12-17 18-23 24-29 30-35 36-41 42-47 48-53 54-59 60+
FIGURE 41 HEIGHTS AND WEIGHTS OF MALNOURISHED GIRLS
FIGURE 42 PERCENT PREVALENCE OF DIARRHEA AND RESPIRATORY
COMPARED TO TOTAL GROUP, JORDAN PEDIATRIC STUDY
INFECTIONS BY AGE AMONG MALNOURISHED CHILDREN AND
126
TOTAL GROUP, JORDAN PEDIATRIC STUDY
127
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
AGE (mos)
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

AGE (mos)

9 characters5 tokens

Aux 2015

Wrong

The x-axis of the first bar graph is the height of the girls.

65 characters18 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

OCR text: TOTAL GROUP 100- 100- 100- 100- 100- 100- 100- 100- 100- 100- 100- 100- 100- 100- 100- 100- 100- 100- 100

115 characters64 tokens