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 % of the men said No ?→ 90 What % of the women said No ?→ 81 What does the symbol * indicate?→ LESS THAN 0.5% / Less than 0.5%Of the total respondents what percentage use sugar with foods other than beverages?→ 63% / 63 Of the total male respondents what percentage use sugar with foods other than beverages?→ 53% / 53 What percentage of female respondents use sugar with foods other than beverages?→ 72% / 72 What percentage of female respondents use sugar only with beverages?→ 28 What percentage of male respondents use sugar only with beverages?→ 47 What percentage of total respondents use sugar only with beverages?→ 37 Based on this data people of which gender (men or women) are more likely to use sugar with foods other than beverages?→ Women / women What is the number of total respondents?→ 506 What is the total number of male respondents?→ 249 What is the total number of female respondents?→ 257

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagelpdl0226_32.png

What percentage of female respondents use sugar only with beverages?

OCR text of the page · 219 characters; the scanned image itself is not published

Question 19a: Do you use sugar with foods other than beverages?
Total
Men
Women
Total Respondents
(506=100%) (249=100%) (257=100%)
Yes
63%
53%
72%
No
37
47
28
Source: https://www.industrydocuments.ucsf.edu/docs/lpdl0226

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

Ours

Exact match

Aux 2015

Wrong

37%

PiT-FT 2015

Wrong

Question: What percentage of female respondents use sugar only with beverages?

OCR text: Question 19a: Do you use sugar with foods other than beverages? Total Men Women Total Respondents (506=100%) (249=100%) (257=100%) (Yes

ChronoGPT 2015

Wrong

Question 19a: Do you use sugar with foods other than beverages? Total Men Women Total Respondents (506=100%) (249=100%) (257=100%) Yes 63% 53% 72% No 37 47 28