Poster Fri, Apr 24, 2026 • 6:30 AM – 9:00 AM PDT Pavilion 4 P4-#3306

Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation

Israfel Salazar ⋅ Manuel Fernández Burda ⋅ Shayekh Islam ⋅ Arshia Soltani Moakhar ⋅ Shivalika Singh ⋅ Fabian Farestam ⋅ Angelika Romanou ⋅ Danylo Boiko ⋅ Dipika Khullar ⋅ Mike Zhang ⋅ Dominik Krzemiński ⋅ Jekaterina Novikova ⋅ Luisa Shimabucoro ⋅ Joseph Marvin Imperial ⋅ Rishabh Maheshwary ⋅ Sharad Duwal ⋅ Alfonso Amayuelas ⋅ Swati Rajwal ⋅ Jebish Purbey ⋅ Ahmed Ruby ⋅ Nicholas Popovič ⋅ Marek Suppa ⋅ Azmine Toushik Wasi ⋅ Ram Mohan Rao Kadiyala ⋅ Olga Tsymboi ⋅ Maksim Kostritsya ⋅ Bardia moakhar ⋅ Gabriel da Costa Merlin ⋅ Otávio Coletti ⋅ Maral Jabbarishiviari ⋅ MOHAMMADAMIN FARAHANIFARD ⋅ Silvia Fernandez ⋅ María Grandury ⋅ Dmitry Abulkhanov ⋅ Drishti Sharma ⋅ Andre Guarnier De Mitri ⋅ Leticia Marchezi ⋅ Setayesh Heydari ⋅ Johan S Obando Ceron ⋅ Nazar Kohut ⋅ Beyza Ermis ⋅ Desmond Elliott ⋅ Enzo Ferrante ⋅ Sara Hooker ⋅ Marzieh Fadaee

Project Page

Abstract

The evaluation of vision-language models (VLMs) has mainly relied on English-language benchmarks, leaving significant gaps in both multilingual and multicultural coverage. While multilingual benchmarks have expanded, both in size and language, many rely on translations of English datasets, failing to capture cultural nuances. In this work, we propose Kaleidoscope, as the most comprehensive exam benchmark to date for the multilingual evaluation of vision-language models. Kaleidoscope is a large-scale, in-language multimodal benchmark designed to evaluate VLMs across diverse languages and visual inputs. Kaleidoscope covers 18 languages and 14 different subjects, amounting to a total of 20,911 multiple-choice questions. Built through an open science collaboration with a diverse group of researchers worldwide, Kaleidoscope ensures linguistic and cultural authenticity. We evaluate top-performing multilingual vision-language models and find that they perform poorly on low-resource languages and in complex multimodal scenarios. Our results highlight the need for progress on culturally inclusive multimodal evaluation frameworks.