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

In row 3, what percent of ASR XL will be converted back to Pinnacle ?→ 50 In row 6, what percent of ASR XL will be converted back to Pinnacle ?→ 75 What is the value in the first column of the row that shows 'dont have ASR XL ' in the corresponding column ?→ 22 What is the value in the first column of the row that shows a corresponding percentage of conversion in the range 70-80 ?→ 26 How many rows are numbered serially in the table ?→ 27 What is the value in the first column of the row that has a percentage value of 0 in the corresponding column ?→ 16 Which alphabet is in the topmost row of the table ?→ S Rows with value 7 and 19 in the first column, have the same percentage value. What is the percentage value ?→ 100 What is the title of the bar graph?→ Likelihood to use Ultamet XL / Likelihood to use ultamet XL According to the bar graph what percent of people are ' extremely ' likely to use ultamet XL ?→ 36% / 36 According to the bar graph what percent of people are ' very ' likely to use ultamet XL ?→ 55% / 55 According to the bar graph what percent of people are ' not at all ' likely to use ultamet XL ?→ 0% / 0 According to the bar graph what percent of people are ' somewhat ' likely to use ultamet XL ?→ 9 % / 9 / 9%

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagermwn0226_79.png

Which alphabet is in the topmost row of the table ?

OCR text of the page · 277 characters; the scanned image itself is not published

11. If yes, what percent
of your ASR XL will
convert back to
1 Pinnacle?
3
50
75
75
00
30%
0%
50
25%1
80%
O
90
100
30%|
2 Dont have ASR XL
25%
50
30
27
30
DM
P-09686-00079
PROTECTED DOCUMENT. DOCUMENT SUBJECTTO PROTECTIVE ORDERtrydocuments.ucsf.edu/docs/rmwn0226
DEPUY023041999

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

Wrong

Aux 2015

Wrong

If yes, what percent of your ASR XL will convert back to 1 Pinnacle?

30%|

2 Dont have ASR XL

25%

P-09686-000

PiT-FT 2015

Wrong

Empty response.

ChronoGPT 2015

Wrong

1 Pinnacle 2 Dont have ASR XL 3 Dont have ASR XL 50% 75% 75% 00% 30% 50% 75% 00% 50% 75% 50% 75% 75% 75% 75%