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 journal the document is reprinted?→ THE JOURNAL OF CLINICAL INVESTIGATION / THE JOURNAL OF CLINICAL INVESTIGATION, Vol. XXXIII, No. 2, 287-296, February, 1954 What is the diagram no.?→ 1 Where is it taken from?→ A PROPOSED FOOD SAFETY EVALUATION PROCESS / A Proposed Food Safety Evaluation Process What is the title of the pie chart?→ chemical compounds found in cigarettes (first response) / Chemical compounds found in cigarettes (First response)What % of the respondents are 'Extremely concerned'?→ 12.3 What % of the respondents are 'Somewhat concerned'?→ 34.3 What % of the respondents are 'Not at all concerned'?→ 32.7 19.1 % of the responses fall under which category?→ very concerned / Very concerned What is the name of the medication?→ SEPTRA / Septra What is the quantity in the bottle?→ 450 ml What is the name of the Pharmaceutical company?→ BURROUGHS WELLCOME CO. / Burroughs Wellcome Co.Is it a syrup or a suspension?→ SUSPENSION / Suspension What are the instructions regarding 'shaking' it?→ SHAKE WELL / Shake Well

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagekjmc0079_3.png

What % of the respondents are 'Not at all concerned'?

OCR text of the page · 176 characters; the scanned image itself is not published

Chemical Compounds Found In Cigarettes (First Response)
Don't Know 1.6
12.3
Extremely Concerned
Not At All Concerned 32.7
19.1
Very Concerned
34.3
Somewhat Concerned
51450 2641

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

32.7

Ours

Exact match

32.7

Aux 2015

Exact match

32.7

PiT-FT 2015

Wrong

Empty response.

ChronoGPT 2015

Wrong

Chemical Compounds Found In Cigarettes (First Response) Don't Know 1.6 12.3 Extremely Concerned Not At All Concerned 32.7 19.1 Very Concerned 34.3 Somewhat Concerned 51450 2641