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 · pagezlfv0228_16.png

For Dopamine, prenatal plot, what is the highest value shown on the Y axis?

OCR text of the page · 681 characters; the scanned image itself is not published
N. DETERING ET AL.
DOPAMINE ( Prenatal )
NOREPINEPHRINE ( Prenatal)
800-
700-
300-
600-
500-
200
ng/g
300-
00-
200
100-
-4-2 BIRTH I WEEK 2 WEEK 3 WEEK'
4-2 BIRTH I WEEK 2 WEEK 3 WEEK
Fig. 3a. . Brain catecholamine concentration in the prenatal experimental
group. For explanation of experimental conditions, symbols,
and statistical significance, see Fig. 2.
DOPAMINE (Postnatal)
NOREPINEPHRINE (Postnotal)
700
300
600-
500-
200-
300-
100-
200-
1001
BIRTH IWEEK 2 WEEK 3 WEEK
BIRTH I WEEK 2 WEEK 3 WEEK
Fig. 3b.
Brain catecholamine concentration in the postnatal experimental
group. For explanation of experimental conditions, symbols,
and statistical significance, see Fig. 2.
15
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
800
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

800

3 characters4 tokens

Aux 2015

Wrong

The highest value shown on the Y axis is 15.

44 characters14 tokens

PiT-FT 2015

Wrong

<|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|>

120 characters64 tokens

ChronoGPT 2015

Wrong

Norepinephrine (Norepinephrine) Norepinephrine (Norepinephrine) Norepinephrine (Norepinephrine) Norepinephrine (Norepinephrine) Norepinephrine (Norepinephrine) Norepinephrine (Norepinephrine

190 characters64 tokens