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 · pageyscw0217_265.png

What is the title of Table 1 ?

OCR text of the page · 448 characters; the scanned image itself is not published
Table 1. Baseline Clinical Characteristics of Study Participants (n=20)
Age, y, mean + SD
52 + 6
Years since menopause, mean + SD
4+3
Body mass index, kg/m , mean + SD
26.1 + 3.2
CAD Risk Factors
Hypercholesterolemia (Serum Chol > 200mg/dL). n
12
Diagnosed Type II Diabetes. n
4
Hypertension (Grade II or Greater), n
0
Current Cigarette Smoking, n
7
Family History, n
14
21
Source: https://www.industrydocuments.ucsf.edu/docs/yscw0217
DWRITE 068076
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
baseline clinical characteristics of study participants (n=20)Baseline Clinical Characteristics of Study Participants (n=20)
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

Baseline Clinical Characteristics of Study Participants (n=20)

62 characters13 tokens

Aux 2015

Wrong

Table 1. Baseline Clinical Characteristics of Study Participants (n=20)

Age, y, mean + SD 52 + 6 Years since menopause, mean + SD 4 + 3 Body mass index, kg/m , mean + SD 26.1 + 3

179 characters64 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

Table 1. Baseline Clinical Characteristics of Study Participants (n=20) Age, y, mean + SD 52 + 6 Years since menopause, mean + SD 4+3 Body mass index, kg/m , mean + SD 26.1 + 3.2 C

180 characters64 tokens