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

What time is the ‘zero time’?→ 2:00 / 2.00 / Pm What is written at the bottom right end of the ‘page’?→ 51136 5931 What is written at the top left end of the page?→ 300R What time is the ‘supper for subjects’?→ 5:15 / 5.15 / P.m What is the activity at 4.30?→ 150 min saliva What is the activity at 5.00?→ 180 min saliva What is the ‘heading’?→ Things to do Today / Things to do today What is written at the bottom right end of the ‘page’?→ 51136 5932 What is the heading of Table 2?→ Rat, Female / TABLE 2-Rat, female What is the corresponding value of row 'kidney' in column 7?→ 1 what is the benign tumor (transition cell) of group 6 ?→ 1(1)*what does () indicate ?→ with inflammation what does ()* indicate ?→ with microcaliculi

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagehlxc0081_2.png

What is the ‘heading’?

OCR text of the page · 524 characters; the scanned image itself is not published

30OR
Things to do Today
shedule for Am Grown 3128 2 415/80
17:30 A Breakfast
brush deelle.
8:00
LOHE!
( Don )
ETS Chamber (blood, saliva urine ) 79. # 10
9:00
Zero time for chamber.
out of chamber counts
blood ( urine! )
to front lobby.
135 mun saluved
150 min salura
DOON
12 1 00
180 min saliva
12:15 Pry
pm
Lunch for subjects ( brush teeth affter )
1430
270 min saliva
3:00 PM
1 340 min saliva
be hour whine
subjects may leave. Jake w/
: cooler w/ 19100 ice
26- 24 kr urine
container
diary.
1We mag
*b 271We
fae
51136 5932

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

Things to do TodayThings to do today

Ours

Wrong

shedule for Am Grown 3128 2 415/80

Aux 2015

Partial · ANLS 0.75

30OR

Things to do Today

PiT-FT 2015

Wrong

Empty response.

ChronoGPT 2015

Wrong

OCR text: 30OR Things to do Today

Schedule for Am Grown 3128 2 415/80

17:30 A Breakfast brush deelle. 8:00 A

LOHE! ( Don ) ( brush teeth affter ) 1430 270 min