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 · pageljwd0228_1.png

Who are they using to evaluate the safety of pesticides and chemicals?

OCR text of the page · 366 characters; the scanned image itself is not published
USE OF HUMAN SUBJECTS IN SAFETY EVALUATION
OF PESTICIDES AND FOOD CHEMICALS
GILBERT BOND
PREPUBLICATION DRAFT
December 1964
A Report of the
Ad Hoc Subcommittee on Use
of Human Subjects in Safety Evaluation
Food Protection Committee
National Academy of Sciences-
National Research Council
Washington, D. C.
Source: https://www.industrydocuments.ucsf.edu/docs/liwd0228
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
human subjectsHuman Subjects
Models
4 of 4 columns · click a model to add or remove it

Ours

Wrong

Ad Hoc Subcommittee on Use of Human Subjects in Safety Evaluation Food Protection Committee National Academy of Sciences-National Research Council

146 characters23 tokens

Aux 2015

Wrong

The use of human subjects in safety evaluation of pesticides and food chemicals is evaluated by the Ad Hoc Subcommittee on Use of Human Subjects in Safety Evaluation of Pesticides and Food Chemicals, which was established by the National Academy of Sciences- National Research Council (NAS- NRC) in 1964

303 characters64 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

ChronoGPT

Question:

What are the reasons for the use of human subjects in safety evaluation?

OCR text: USE OF HUMAN SUBJECTS IN SAFETY EVALUATION GILBERT BOND

Question:

180 characters64 tokens