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 · pagemtjm0081_13.png

What is the title of the flowchart?

OCR text of the page · 486 characters; the scanned image itself is not published
51360 2211
. Organizational Structure for the SMOKERS EXPRESS Group of Companies
SMOKERS EXPRESS, Inc
SE
PUBLICATIONS
SE AIR
SE
SE
PRODUCTS
SE SERVICES
VACATIONS
In-flight Magazine
Charter Airline
SE Air Tickets
In-flight
Merchandise Sales
In-flight Catering
Sales
Catalog Production
Maintenance
Travel and
Vacation Services
Catalog Sales
Ground Support
and Distribution
Services
Maintenance
Crew Services
Company Meeting
and Convention
Support
Services
Security
Membership
Solicitation
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
organizational structure for the Smokers Express group of companiesOrganizational structure for the SMOKERS EXPRESS Group of Companies
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

Organizational Structure for the SMOKERS EXPRESS Group of Companies

67 characters13 tokens

Aux 2015

Wrong

SMOKERS EXPRESS, Inc

20 characters7 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

ChronoGPT, a large language model trained by Manela Lab at WashU, is a language model trained by Manela Lab at WashU.

Question:

What is the title of the flowchart?

ChronoGPT, a large language model trained

212 characters64 tokens