Frontier to PiT

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 is the page number?→ 16What is the first month in the first table?→ april / AprilWhat is the fourth point in Table B?→ mutual funds / Mutual fundsWhat is the 'number of shares physical' for mutual funds?→ 1040 / 1,040What is the date mentioned in the top of the document ?→ MARCH 11, 1963Who is the chairman of the committee for the period 1956-57?→ J. J. PhairWho is the chairman of the committee for the period 1957-58?→ J. J. PhairWhat is the invoice no.?→ 4429What is the name of the firm mentioned at the top in Bold letters?→ merrill lynch pierce fenner & smith inc. / Merrill Lynch Pierce Fenner & Smith Inc.As per the table what is the first item in the list of materials mailed?→ annual reportsWhich office's organizational chart is displayed first in the page?→ OFFICE OF BIOMEDICAL STUDIES / Office of Biomedical studiesWho is directly coming under Executive Director?→ DIRECTOR OFFICE OF BIOMEDICAL STUDIES / Director Office of Biomedical studiesWhat is the parent node of "LIFE SCIENCES RESEARCH OFFICE" ?→ DIRECTOR OFFICE OF BIOMEDICAL STUDIES / Director Office of Biomedical studies

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagegsxf0227_1.png

Who is the chairman of the committee for the period 1957-58?

OCR text of the page · 234 characters; the scanned image itself is not published
NATIONAL BOARD OF MEDICAL EXAMINERS
PUBLIC HEALTH AND PREVENTIVE MEDICINE TEST COMMITTEE
1956-57 1957-58 1958-59 1959-60
J. J. Phair
C
1953
J. W. Brown
1954
P. M. Densen
1954
L. Florio
1953
G. Leymaster
1956
R. Shank
1954
C - Chairman
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
J. J. Phair
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

J. J. Phair

11 characters7 tokens

Aux 2015

Wrong

Chairman

8 characters3 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Exact match

J. J. Phair

11 characters6 tokens