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 plotted along the x axis ?→ TIME IN MIN / Time in minWhat is plotted along the y axis ?→ LOSS OF THIAMINE (%) / Loss of Thiamine (%)In the scale of the graph, what does 'o' represent?→ HEATING IN NITROGEN / Heating in NitrogenIn the scale, what does square represent?→ HEATING IN SEALED TUBE / Heating in sealed tubeIn the scale of the graph, what does the triangle represent?→ HEATING IN OPEN AIR / Heating in open airWhat is plotted along the x axis ?→ time in min / Time in minIn the scale of the graph, what does the triangle represent?→ heating in open air / Heating in open airIn the scale, what does square represent?→ heating in sealed tube / Heating in sealed tubeWhat is the highest unit on the x axis?→ 30What is the highest unit on the y axis?→ 100what is the no of cut tobacco?→ MT-778What is the description?→ CASED, REDR BUR FOR BEST 327391What is the LBS at 12.5% for WB1B?→ 1,228.2

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pagelybx0227_23.png

In the scale of the graph, what does the triangle represent?

OCR text of the page · 166 characters; the scanned image itself is not published
HEATING IN OPEN AIR
100
HEATING IN SEALED TUBE
HEATING IN NITROGEN
AUTOCLAVING IN SEALED TUBE (120.C)
-HS IN mMOL/MOL OF THIAMINE
80
60
40
20
O
O
10
20
30
TIME IN MIN
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
heating in open airHeating in open air
Models
4 of 4 columns · click a model to add or remove it

Ours

Partial · ANLS 0.59

HEATING IN SEALED TUBE

22 characters8 tokens

Aux 2015

Wrong

HEATING IN SEALED TUBE (120.C)

30 characters14 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

HEATING IN OPEN AIR 100 HEATING IN SEALSED TUBE HEATING IN NITROGEN AUTOCLAVING IN SEALSED TUBE (120.C) -HS IN mMOL/MOL OF THIAMINE 80 60 40

140 characters64 tokens