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 · pagemyjf0004_2.png

What is the Ship Date ?

OCR text of the page · 915 characters; the scanned image itself is not published
HEALTH EXAMINATION AND CLINICAL OBSERVATION
(CONDUCTED DURING QUARANTINE)
Study Number_OX (2684&B
Study Director Dan Meckley
Packing Slip Description
Packing Slip Description
Number of Animals_565
Number of Animals
Species/Strain Mouse / Se near species/strain
Sex Female
Sex
Weight Range ( weeks Weight Range
Animals Received 5 90
Animals Received
(actual number)
(actual number)
Packing Slip Identifiers
Supplier and controls Harlan Sprague Dawley
RJR P. O.# 1010
ship Date:
3- 27 - 95
To Be Filled Out By Laboratory Animal Veterinarian
On
march 30, 1995
(date)
I examined the above shipment of
animals. There were no observable clinical abnormalities which
would preclude these animals from being placed on study.
David Small
3 30 95
Diplomate, A. C.L.A.M.
Date
Laboratory Animal Veterinarian
cc: Study Director
Jessica Baker
51831 1473
Sheri Reynolds
Source: https://www.industrydocuments.ucsf.edu/docs/myjf0004
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
3-27-95
Models
4 of 4 columns · click a model to add or remove it

Ours

Partial · ANLS 0.70

3- 27 - 95

10 characters10 tokens

Aux 2015

Exact match

3-27-95

7 characters8 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

OCTOBER 30, 1995

OCTOBER 30, 1995

OCTOBER 30, 1995

OCTOBER 30, 1995

OCTOBER 30, 1995

OCTOBER 30, 1995

Input:

Question

132 characters64 tokens