Modular Ebbinghaus Benchmark for LLMs and Human Participants

Zenodo (CERN European Organization for Nuclear Research) 2026 Open access

Read full text
Authors: Yann Cohen
DOI: 10.5281/zenodo.18906801
Cited by: 0

Abstract

First stable release of the Modular Ebbinghaus Benchmark - a full R toolkit for generating Ebbinghaus illusion stimuli and evaluating vision-language model (VLM) accuracy. Includes complete source code, example trial tables (CSV), and sample stimulus images.

Fields of Study & Subjects

Visual perception and processing mechanisms Multimodal Machine Learning Applications Categorization perception and language

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
8 March 2026
Language
EN