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

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pageflwl0079_12.png

What is the page number?

OCR text of the page · 916 characters; the scanned image itself is not published
ATTACHMENT III
XG FF/FELT NM 85MM DIRECTION FOR IMPROVEMENT
FF NM 85MM
Prototype 1 (#886 B)
Prototype 2 (#886 C)
ETA
ETA
Smoother
39
Less Harsh
40
Less Harsh
.36
More Tobacco Taste
. 39
More Tobacco Taste
35
Smoother
. 38
Less Strong Aftertaste
.34
Less Strong Aftertaste
.35
Fresher Aftertaste
33
Less Dry Aftertaste
.33
Milder
.32
Less Sour Aftertaste
.33
Less Sour Aftertaste
. 32
Fresher Aftertaste
.33
Less Dry Aftertaste
.31
Sweeter Taste
.31
FFLT NM 85MM
Prototype 1 (#887 B)
Prototype 2 (#887 c)
ETA
ETA
Less Strong Aftertaste
. 51
Smoother
. 40
Less Harsh
877
Fresher Aftertaste
. 39
More Tobacco Taste
48
Less Lasting Aftertaste
,39
Smoother
.45
Less Strong Aftertaste
, 39
Less Lasting Aftertaste
.44
Less Dry Aftertaste
34
Less Strength
.44
Less Harsh
.33
Fresher Aftertaste
. 40
Less Sour Aftertaste
. 32
Milder
.39
More Tobacco Taste
31
Less Dry Aftertaste
. 38
Less Sour Aftertaste
.37
50572 6283
-11-
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
11
Models
4 of 4 columns · click a model to add or remove it

Ours

Partial · ANLS 0.50

-11-

4 characters5 tokens

Aux 2015

Wrong

ATTACHMENT III XG FF/FELT NM 85MM DIRECTION FOR IMPROVEMENT FF NM 85MM Prototype 1 (#886 B) Prototype 2 (#886 C) ETA ETA Smoother 39 Less Har

141 characters64 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

Attachment III XG FF/FELT NM 85MM DIRECTION FOR IMPROVEMENT Attachment III XG FF/FELT NM 85MM DIRECTION FOR IMPROVEMENT Attachment III Attachment III Attachment III Attachment III Attachment III Attachment

205 characters64 tokens