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

What is the first item listed in the ‘agenda’?

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
Circular of January 31stGodchaux’s objectionsProud foot,China’s reports
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

Circular of January 31st

24 characters8 tokens

Aux 2015

Wrong

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
199 characters64 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters1 tokens

ChronoGPT 2015

Wrong

Stone - Book Bruyn Patterson Taylor Van Buren ENFORCEMENT COMMITTEE MEETING February 6th, 1930 AGENDA

  1. Circular of January 31st Proudfoot, Chinal Reports Grocers Term. ( Sthouis ) 2
183 characters64 tokens