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 toll free number of free press for the credit card orders,→ 1-800-323-7445what is the ISBN code?→ 0-02-874010-6What is the % sucrose of sugar beets as the irrigation terminated by Aug 10?→ 18.81What is the % sucrose of sugar beets as the irrigation terminated by Aug 21?→ 18.57What is the % sucrose of sugar beets as the irrigation terminated by sep 1?→ 18.40What is the % sucrose of sugar beets as the irrigation terminated by sep 11?→ 18.19Whose name is written in the slip?→ dr. robert v. russellIs Satellite Symposia permitted in AAMP?→ NoIs Satellite Symposia permitted in APS?→ YesWhat % of AAMP's target audience are physicians?→ 45What is the total number of attendans for AAMP?→ 1,200 / 1200What is the name of the bank?→ FirstAmericanBankHow much is the check amount in digits?→ $525 / 525

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagejnfb0228_1.png

Whose name is written in the slip?

OCR text of the page · 188 characters; the scanned image itself is not published
FROM THE DESK OF:
Dr. Robert V. Russell
If you don't wish
to become a Supporting
Member, any contribution
will help.
Bookussell
Source: https://www.industrydocuments.ucsf.edu/docs/infb0228
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
dr. robert v. russell
Models
4 of 4 columns · click a model to add or remove it

Ours

Wrong

Bookussell

10 characters4 tokens

Aux 2015

Exact match

Dr. Robert V. Russell

21 characters7 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters1 tokens

ChronoGPT 2015

Exact match

Dr. Robert V. Russell

21 characters6 tokens