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 · pagegxyd0217_10.png

Who approves study budgets based on sub-title "Site specifics" ?

OCR text of the page · 1,263 characters; the scanned image itself is not published
* Former Director of the Framingham diabetics
women
Heart Strly
SITE SELECTION CRITERIA FOR Atorvastatin
9
PHASE
IIIB/TV INVESTIGATORS
THIS FORM IS TO BE COMPLETED IN ITS ENTIRITY FOR THOSE PHYSICIANS
YOU WOULD LIKE TO HAVE CONSIDERED FOR THE MEDICAL RESEARCH
PHASE IIIB/TV TROGLITAZONE PROGRAMS.
Doctor's Name:
Address:
William Castelli, MD
Cardiovascular Institute: Wellness Center
Phone:
Meth - weet Hosp. Framinghim ( men Canyes
115 Lincoln 57
7508) 383 - 8680
Framingham MA 01 701-9167
Study Coordinator(s):
sending - laura mercer, RN
Practice Specialty:
CD
Study experience:
extensive
PD studies:
- was asnational speaker for pp
Number of active studies:
Any competing studies:
Lipid Population:
# of patients in practice
500 - 1000
most common treatment
# of newly diagnose
HmGs clues , LOPID
10-15/mmv7
method of recruitment
Site specifics:
could site ID 20-30
pts in 6 months? (Y/N) _
where are study records stored? / locked Cabinet
where are study drugs stored? _
is the drug storage locked? (Y/N)_
central lab experience?(who)
RB requirements, can a national IRB be used? No
Local IRB meeting schedule
once/ month
who approves study budgets? himselz
Comments:
CBU Associate Director:
Phone:
Source: https://www industrydocuments.ucsf.edu/docs/gxydo217
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
Himselfhimself
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

himself

7 characters3 tokens

Aux 2015

Wrong
  • Former Director of the Framingham diabetics women Heart Strly SITE SELECTION CRITERIA FOR Atorvastatin 9 PHASE IIIB/TV INVESTIGATORS THIS FORM IS TO BE COMPLETED IN ITS ENTIRETY FOR THOSE PHYSICIANS YOU WOULD LIKE TO HAVE CONSIDERED
234 characters64 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

OCR text:

Study Details

Study Details

Study Details

Study Details

Study Details

Study Details

Study Details

Study Details

Study Details

Study Details

Study Details

Study Details

237 characters64 tokens