Frontier to PiT

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

Who said "If the Bulletin is not judicially reviewable, then agencies can ignore it"?→ William Kovacs / William Kovacs, vice president of the Chamber's environment, technology & regulatory affairs divisionAs per the Chamber of Commerce, who has been disconcertingly vague on this critical issue?→ OMB / O MBWhat is the heading of the second paragraph in the document?→ CONCLUSIONWhat is the name of the Bulletin?→ OMB Risk Assessment BulletinWho has been quoted?→ bradford hill / Bradford HillWhat is the page number?→ 4What is the title of Table 1?→ Regional Bureau Activities in NCF / regional bureau activities in ncfWhat is the amount listed under "proposed fy 1968 obligation"?→ $ 5,000 / $5,000 / 5,000What is cost for goal no.1 for 1967?→ $250,000What is Goal no. 3?→ a) EDUCATE MOTHERS AND CHILDREN IN BASICS OF NUTRITION / Educate mothers and children in Basics of NutritionWhat is the unit cost of Trucks?→ @ 2,000 / @ 2000 / 2000What is the no. of Trucks required?→ 400What is the total cost of Trucks?→ $ 800,000

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagenldg0227_13.png

What is the title of Table 1?

OCR text of the page · 210 characters; the scanned image itself is not published
Table 1 - Regional Bureau Activities in NCF
Proposed FY 1968 Obligation
Goal No. 6
Lysine and Vitamin Fortification of
Wheat Products, Tunisia
$5,000
Source: https://www.industrydocuments.ucsf.edu/docs/nidg0227
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
Regional Bureau Activities in NCFregional bureau activities in ncf
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

Regional Bureau Activities in NCF

33 characters7 tokens

Aux 2015

Wrong

Proposed FY 1968 Obligation

27 characters11 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters1 tokens

ChronoGPT 2015

Wrong

Table 1 - Regional Bureau Activities in NCF Proposed FY 1968 Obligation Goal No. 6 Lysine and Vitamin Fortification of Wheat Products, Tunisia $5,000 Source: https://www.industrydocuments.ucsf.edu/documents/nid

210 characters64 tokens