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 · pagekslw0227_3.png

What draft is it, preliminary or final?

OCR text of the page · 191 characters; the scanned image itself is not published
CONDENSED VERSION--FINAL DRAFT
PHYSIOLOGIC ADJUSTMENTS IN GENERAL
Prepared for "Laboratory Indices of
Nutritional Status in Pregnancy."
Roy M. Pitkin, M. D.
rydocuments.ucsf.edu/docs/kslw0227
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
finalfinal draftFinalFinal draft
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

FINAL DRAFT

11 characters4 tokens

Aux 2015

Exact match

FINAL

5 characters2 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters1 tokens

ChronoGPT 2015

Wrong

Pre-Draft

Final Draft

29 characters8 tokens