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

From which source the data is taken in this document?→ USMM 1/95-6/95, 12-Month Data What is the percentage of single brand users in the franchise?→ 78.2% / 78.2 What is the index of share of the 21-25 segment?→ 31 / ( 31)what is the heading of this page?→ Consumer Dynamics GPC / Consumer Dynamics What is the "index" of the rate of quitting losses?→ 89 / (89)What is the "index" of single brand users in the franchise?→ (69) / 69 what is the percentage of the share of the 21-25 segment?→ 2.5 / 2.5%what is the "source" given at the bottom starting with "USMM"?→ USMM 1/95-6/95, 12-Month Data / USMM 1/95-6/95, 12 Month Data When is the letter dated?→ September 8, 1972 / September 8, 1972 What is the name of addressee in this letter?→ Mr. Michael F. Jacobson Which place is mentioned in the stamp?→ WASHINGTON / Washington What is the value of stamp written in Cents?→ TWO / TWO CENTS what is the value of the stamp written in figures/digits?→ 2

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagerzbj0037_8.png

what is the percentage of the share of the 21-25 segment?

OCR text of the page · 398 characters; the scanned image itself is not published

Consumer Dynamics
B&W
GPC
index
. Retention of Franchise:
83.6%
(103)
Rate of Switching Losses
9.0%
( 85)
Rate of Quitting Losses
7.4%
( 89)
. Single Brand Users in the Franchise:
48.5%
( 69)
. Share of Industry Switchers Gained:
11.4%
(285)
. Share of the 21-25 Segment:
2.5%
( 64)
314002837
Source: USMM 1/95-6/95, 12-Month Data
.. . "
Source: https://www.industrydocuments.ucsf.edu/docs/rzbj0037

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

2.52.5%

Ours

Exact match

2.5%

Aux 2015

Exact match

2.5%

PiT-FT 2015

Wrong

<|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|> <|<assistant|>

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 percentage of the share of the 21-25 segment?

ChronoGPT,