Table · dataset · 2026
PaulineLi/QuantiPhy
Listed in Hugging Face Datasets
QuantiPhy Dataset
Description
Summary
QuantiPhy is a benchmark for evaluating whether vision–language models (VLMs) can perform quantitative physical inference from visual evidence, rather than producing plausible but ungrounded numerical guesses. This repository contains the official test set of the QuantiPhy benchmark, consisting of 3,289 video–question (QA) pairs across 568 videos. Ground-truth answers are withheld to ensure fair evaluation.
Read the rest (1 more)
Each instance requires a model… See the full description on the dataset page: huggingface.co/datasets/PaulineLi/QuantiPhy.
Links
Where it is published
- Hugging Face dataset page huggingface.co/datasets/PaulineLi/QuantiPhy ↗
landing page · from Hugging Face
Documentation and papers
- arXiv:2512.19526 arxiv.org/abs/2512.19526 ↗
publication · from Hugging Face
Catalogue records · 1
- Hub API huggingface.co/api/datasets/PaulineLi/QuantiPhy ↗
metadata API · from Hugging Face
Topics
- Stated by source
- text · video · video text to text · visual question answering
- From keywords
- Computer Science & AI
- Inferred from text
- Video 75%
Provenance · 1 source records, 13 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Hugging Face Datasets | PaulineLi/QuantiPhy | 14 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · Hugging Face | connector:huggingface@1.0.0 | /gated |
| concepts[field].local:field:computer-science-ai | mapping · Hugging Face | connector:huggingface@1.0.0 | |
| concepts[modality].hf_modality:text | source · Hugging Face | connector:huggingface@1.0.0 | |
| concepts[modality].hf_modality:video | source · Hugging Face | connector:huggingface@1.0.0 | |
| concepts[modality].local:modality:video | enrichment · Hugging Face | keyword-concept-rules@1.0.0 | title+description (75%) |
| concepts[task].hf_task:video-text-to-text | source · Hugging Face | connector:huggingface@1.0.0 | /tags[task_categories:*] |
| concepts[task].hf_task:visual-question-answering | source · Hugging Face | connector:huggingface@1.0.0 | /tags[task_categories:*] |
| created_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| description | source · Hugging Face | connector:huggingface@1.0.0 | /description |
| license | source · Hugging Face | connector:huggingface@1.0.0 | /tags[license:*] |
| publication_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| title | source · Hugging Face | connector:huggingface@1.0.0 | /id |
| updated_date | source · Hugging Face | connector:huggingface@1.0.0 |