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 Regimen C "n" value for Days 1.1-2?→ 64What is the Regimen C "n" value for Days 2.1-3?→ 45What is the Regimen C "n" value for Days 3.1-4?→ 26What is the Regimen C "n" value for Days 4.1-5?→ 12What is the Regimen C "n" value for Days 5.1-6?→ 3What is the Regimen C "n" value for Days 6.1-7.5?→ 3What is the Regimen D "n" value for Days 7.6-11?→ 2What is the Regimen D "n" value for Days 2.1-3?→ 45What is the Regimen D "n" value for Days 3.1-4?→ 36What is the title?→ ballot / BALLOTWho is number 1 among the list of nominees listed?→ John B. YoumansWho is number 2 among the list of nominees listed?→ W.H. Sebrell, Jr.Who is number 3 among the list of nominees listed?→ R.W. Engel

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagezqdw0217_14.png

What is the Regimen D "n" value for Days 7.6-11?

OCR text of the page · 610 characters; the scanned image itself is not published
Table 3. Mean Change in Onset of Withdrawal Bleeding/Spotting
Between Consecutive Cycles
2-day biopsy window
Regimen
C
Regimen
D
Cumulative
Cumulative
Days
n
n
n
n
0 - 1
4 4
22.3
24
13.1
1. 1-2
64
32.5
108
54.8
51
27.9
75
41.0
2. 1-3
45
22.9
153
77.7
45
24.6
120
65.6
3. 1-4
26
13.2
179
90.9
36
19.6
156
85.2
4. 1-5
12
6. 1
191
97.0
1 8
174
95.1
5. 1-6
3
1.5
194
18.5
5
2.7
179
97.8
6. 1-7.5
3
1.5
197
100
2
1. 1
181
98.9
7.6-11
2
1. 1
183
100
Note: Amenorrheic cycles among patients in treatment groups C and D were not included in this
analysis.
Confidential Pursuant to Confidentiality
PCSAR002-002151
Order
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
2
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

2

1 characters2 tokens

Aux 2015

Wrong

1

1 characters2 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

Regimen D n n n n n n n n n n n n

33 characters27 tokens