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

Whose design is the Met Mirror?→ Neal Martz's design / Neal Martz / Neal Martz's What is written on one half of the bottle in the last picture?→ Quality Who had signed the Demond Heeley’s Design for Don Pasquale?→ Mr. Heeley What is the ‘title’ of M.Wigren?→ SECRETARY / Secretary What is the ‘salary’ of M.Wigren?→ $5,589 What is the ‘title’ of B. Levine,Ph.D.?→ NUTRITION DIRECTOR / Nutrition Director What is the ‘salary’ of B. Levine,Ph.D.?→ 15,803 / $15,803 What is the ‘title’ of R. Tannenbaum, Ph.D?→ PROGRAM EVALUATOR / Program Evaluator What is the ‘salary’ of R. Tannenbaum, Ph.D?→ 20,000 / $20,000 How much is the estimated amount for ‘computer time’ in supplies and services?→ 5,000 / $5,000 How much is the estimated amount for ‘keypunch ’ in supplies and services?→ 3,000 / $3,000 How much is the ‘total personnel’ amount estimated in the budget?→ 47,047 / $47,047 How much is the TOTAL amount estimated in the budget?→ $75,176

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagenjxw0228_9.png

What is the ‘salary’ of B. Levine,Ph.D.?

OCR text of the page · 558 characters; the scanned image itself is not published

ESTIMATED BUDGET
for
Nutrition Education of Physicians Proposal
THIRD YEAR
(January 1, 1987-December 31, 1987)
Personnel
Fringe
Title
Benefits
Total
Secretary
8
Salary
M. Wigren
$5,589.
$1, 230.
$6, 819
B. Levine, Ph.D.
Nutrition
40
15,803.
4, 425.
20, 228.
Director
R. Tannenbaum, Ph. D. Program
20,000.
20,000.
Evaluator
47,047.
Supplies and Services
Computer time
5,000.
Keypunch
3,000.
Post test printing (10,000, copies)
2, 600.
Postage
5,000
15,600.
Total Personnel
47,047.
Total Supplies & Services
15,600.
Indirect Costs (208)
12,529.
TOTAL
$75, 176.

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

15,803$15,803

Ours

Partial · ANLS 0.88

$15,803.

Aux 2015

Wrong

$75,176

PiT-FT 2015

Wrong

ChronoGPT 2015

Wrong

$5,589.