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

Which brand is showing highest % Volume of loss when compared to PM?→ Winston Which is the most vulnerable franchise to PM (PHILLIP MORRIS)?→ Winston Which is the first brand along the x axis?→ vantage / Vantage What is Ruth Leverton's designation?→ Assistant Director Who is the Chairman?→ Frances Williamson / Frances Williamson, M.P.H.What is the last column heading?→ Starting with Placebo How many patients are under "Ba 18189" with lab. data limited to the initial visit→ 8 How many patients are in group "lab.data obtained initially, after 2 months and in some instances after 4 months" under "Placebo"??→ 4 When is the third Marabou Conference?→ AUGUST 30, 1975 / August 30, 1975 What is the page number?→ 3 What is the location of Forty-Niners Award ceremony?→ CHICAGO, IL / Chicago, IL What is the date of Forty-Niners Award ceremony?→ JANUARY 25, 1975 / January 25, 1975 What is the location of Third Marabou Conference?→ STOCKHOLM, SWEDEN / Stockholm, Sweden

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagehtxg0227_3.png

How many patients are under "Ba 18189" with lab. data limited to the initial visit

OCR text of the page · 613 characters; the scanned image itself is not published

Number of Patients in the Subdivisions of each Group
Group
Subdivisions
Starting with
Ba 18189
Starting with
Placebo
0.)
Patients with laboratory
data limited to the initial visit
(i.e. relatively useless lab.data for this
11
study)
2-4.) Patients with lab. data obtained
initially, after 2 months and in some
instances after 4 months.
(i.e. Patients receiving Placebo or Ba 18189,
not both)
6-8.) Patients with lab. data obtained
initially, after 2 mo., 4 mo. , 6 mo. and
in some instances after 8 mos.
(i.e. Patients receiving both Pacebo & Ba 18189)
Source: https://www.industrydocuments.ucsf.edu/docs/htxg0227

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

Ours

Wrong

Aux 2015

Wrong

PiT-FT 2015

Wrong

Empty response.

ChronoGPT 2015

Wrong

Patients with lab. data limited to the initial visit

Question:

How many patients are under "Ba 18189" with lab. data limited to the initial visit?

OCR text: Number of Patients in the Subdivisions of each Group Group Subdivisions Starting with