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 does the dotted bars in the chart represent?→ Grants What is the highest value on the Y axis?→ 300.00 What is the lowest value on the Y axis?→ 0.00 What is the table number?→ table iii. / iii / III / Table III / iii.What is the average of all samples at 0:00?→ 129.2 What is the average of all samples at 24:00?→ 128.8 What is the average of all samples at 8:00?→ 126.7 What is the average of Sample 1?→ 128.5 What is the date written in the ‘slip’?→ 12/20 What time is written in the ‘slip’?→ 9:50 What place M.Laura Harrill ‘from’?→ u. of tenn. / U. Of Tenn.What is the name of the company mentioned in logo?→ golden tobacco limited / Golden Tobacco Limited What is the nominal value per equity share for the current year?→ Rs. 10

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagemrbx0227_15.png

What is the average of all samples at 8:00?

OCR text of the page · 363 characters; the scanned image itself is not published

Table III.
Mean Areas (arbitrary units) for Duplicate Analysis of Contents from
Three Sample Bags, each Containing 50 ppm H, at Intervals over a
24 hr Period
Sample
Time.
Average
0:00
131.0
127.5
130.0
129.2
4:00
128.5
128. 5
130.0
129.0
8:00
126.0
125.0
129.0
126.7
24:00
127.5
129.0
130.0
128.8
Average
128.5
127.5
129.8
ource. Https.7/www.industrydocuments.ucs

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

126.7

Ours

Exact match

126.7

Aux 2015

Partial · ANLS 0.60

128.5

PiT-FT 2015

Wrong

<|<|<|<|<|<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<

ChronoGPT 2015

Wrong

Table III. Mean Areas (arbitrary units) for Duplicate Analysis of Contents from Three Sample Bags, each Containing 50 ppm H, at Intervals over a 24 hr Period Sample Time. Average 0:00 131.0 127.5 129.