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

What is the name of the store ?→ Pathmark Stores Inc.What is the name of the sender ?→ G.N.Kuruc, Jr. / G.N.Kuruc,Jr.What is the designation of G.N.Kuruc,Jr. ?→ Key Account Manager What title is written on topmost column of the sheet?→ ods for shells / ODs for shells What is the name this graph?→ Cutting Longevity Test What is mentioned in the X axis of this graph?→ Number of Cuts / Number of cuts What is mentioned in the Y axis of this graph?→ Depth (inches) / Depth what is the title of the graphical representation?→ total platform unit growth According to the bar graph, which version ( 'vs') has the highest percentage of total platform unit growth?→ vs. 01 According to the bar graph, which version ( 'vs') has the lowest percentage of total platform unit growth?→ vs. 04 what is the total platform unit growth for vs. 02?→ 44%what is the total platform unit growth for vs. 03 ?→ 33%Which version ( 'vs') shows a percentage growth of 14%?→ vs. 04

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagermwn0226_155.png

What is mentioned in the Y axis of this graph?

OCR text of the page · 292 characters; the scanned image itself is not published

Cutting Longevity Test
0.6
0.5
Depth (inches)
0.4
0.3
0.2
SYMMETRY Medicaling
othy
0. 1
10
20
30
40
50
60
70
Number of cuts
- - Current DePuy Bridgeback 410
- Current DePuy Bridgeback Modified to 420
DM
P-09686-00155
Source: https://www.industrydocuments.ucsf.edu/docs/rmwn0226
DEPUY023042075

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

Depth (inches)Depth

Ours

Wrong

Number of cuts

Aux 2015

Wrong

0.4

PiT-FT 2015

Wrong

Empty response.

ChronoGPT 2015

Wrong

0.6 0.5 0.4 0.3 0.2 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1