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 · pageghgw0023_5.png

Which material ‘specifications’ is given?

OCR text of the page · 557 characters; the scanned image itself is not published
P.GM: GMC433IN
MANUFACTURING STANDARDS SYSTEM
03/20/97 09:20
PROPRIETARY - 35239
GLYCERINE/GLYCOL SPECIFICATIONS
PAGE 4 OF 7
ITEM-ID. . . . . ...
SPEC REVISION . : AD
EFFECTIVE DATE.
: B-3
EXPIRATION DATE :
: 12/10/96
SPEC STATUS . . .
CURRENT
DESCRIPTION . . . .
: GLYCERIN USP GRADE
MATERIAL GL TYPE: GLYCERINE
REJECT LIMITS
* STORAGE REQUIREMENTS*
TARGET
LOW
HIGH
MAXIMUM STORAGE DURATION, DAYS:
360
STORAGE TEMPERATURE, DEG. F. .
100. 0
70.0
130.0
AGITATION REQUIRED
. . . . . : NO
52338 5920
Source: https://www.industrydocuments.ucsf.edu/docs/ghgw0023
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
GLYCERINE/GLYCOLGlycerine/glycol
Models
4 of 4 columns · click a model to add or remove it

Ours

Partial · ANLS 0.52

GLYCERINE/GLYCOL SPECIFICATIONS

31 characters10 tokens

Aux 2015

Wrong

GLYCERINE/GLYCOL SPECIFICATIONS

Answer: GLYCERINE/GLYCOL SPECIFICATIONS

72 characters22 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

Material Specification

OCR Text:

P.GM: GMC433IN

OCR Text:

Material Specification

OCR Text:

Material Specification

Material Specification

Material Specification

Material Specification

225 characters64 tokens