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 · pagekgjl0226_1.png

How many events are listed in the agenda of the enforcement committee meeting?

OCR text of the page · 727 characters; the scanned image itself is not published
Stone Engle Stubbs White
Bruyn Patterson Taylor
Van Buren
ENFORCEMENT COMMITTEE MEETING
February 6th, 1930
AGENDA
1. Circular of January 31st
Proudfoot, Chinal Reports
Godchaux's objections.
Grocers Term. ( Sthouis )
2. Henderson matter.
Hill whee ( Superior )
OK - submit to all
Stone - Book trying to rom the show
3. Brokers' Pledge. Directors and to
- Douglas telling Beet, how to get
Aissue ,
around rulings . ( aliesen )
4. Hill Transfer & Storage
Letter from Holly
5 .
Define "General Broker"
Stubbs
6 .
Undelivered Balances - 5.10 Contracts
- Feb 1716
Advertising
Taylor - exceptions
Ny Who Gro.
Stone - no Exception
My retail bakers
Dairymens Assoc of Fasterally
Doleat for info Comm.
Establishing loss
4 PM
Cs/kg/10226
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
6
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

6

1 characters2 tokens

Aux 2015

Wrong

1

1 characters2 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters1 tokens

ChronoGPT 2015

Wrong

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

Question:

What is the most important event in the history of the WashU community?

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

219 characters64 tokens