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 · pagekmvd0228_22.png

What is the highest value on the Y axis?

OCR text of the page · 138 characters; the scanned image itself is not published
0.8
360 m
El cm = 47.0
0.1%
0.4+
OPTICAL DENSITY
435 m j
0.2
Elom = 14.7
0.1%
O
5
10
15
20
25
30
MICROGRAMS / ml-E-DNP_LYSINE-HCL
Figure 2
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
0.8
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

0.8

3 characters4 tokens

Aux 2015

Exact match

0.8

3 characters4 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

0.1% 0.2% 0.4% 0.1% 0.1% 0.1% 0.1% 0.1% 0.1% 0.1% 0.1% 0.1% 0.1%

64 characters64 tokens