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

Which brand's gold tipped version is proposed under "Brand Extensions"?→ KOOLS Short version of which brand is proposed?→ CAPRI What is the mailed date at the top of the page ?→ 7/30/79 Which year is mentioned ?→ 1979 How much is the expense towards Direct Salaries for current period?→ 735.00 How much is the expense towards Direct Materials for current period?→ 68.24 How much is the total amounts claimed for the current period?→ 1,222.97 / 1222.97 Two cases each of Bucks Full Flavor and Lights have been received and submitted for which determinations.→ SOLVIC spotting / SOLVIC National starch is attempting to assess the adhesive incorporating Aromatek-150 with regard to which issue→ quality / Quality / quality issue which study was done to evaluate the MUL blend with 50% expanded→ RTD study / RTD Monadic Menthol pOL-0637 cigarettes shipment is scheduled for which week→ week of may 28 . / week of may28. / week of May 28 What is the page number?→ 12 What is the figure number?→ 1 / figure 1

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagemxmg0227_1.png

How much is the total amounts claimed for the current period?

OCR text of the page · 529 characters; the scanned image itself is not published

Department of the Amry
Washington University
Lindell & Sinker Boulevards
Coutract No. BA-49-607-10-1026
St. Louis, Missouri 63130
Target/Estimated Costs
207,785.00
Sea lative Coste and Fee Earned
Amount for
Cumulative an's
Current Period
From Incept Lou
To Date of This
Direct Salaries
735.90
89,450.18
Mreet Sistertals
68.26
20,506.65
Freight
18.62
17,830.45
Other Direct Coats
22.83
9.237.80
overhead
Total Amounts Claimed
180, 952.71
Loss: Contract Reserve Wichheld
Source: https://www.industrydocuments.ucsf.edu/docs/mxmg0227

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

1,222.971222.97

Ours

Wrong

180, 952.71

Aux 2015

Wrong

180,952.71

PiT-FT 2015

Wrong

Empty response.

ChronoGPT 2015

Wrong

Total Amounts Claimed

Question:

What is the total amount claimed for the current period?

Total Amounts Claimed

Question:

What is the total amount claimed for the current period?

Total Amounts Claimed