SU-FMI-AI/ImageCLEF-MR2026-MCQ-Visual

---
license: cc-by-nc-4.0
configs:
- config_name: default
data_files:
- split: test
path: data/test-*
dataset_info:
features:
- name: question_id
dtype: string
- name: type
dtype: string
- name: visual_elements
struct:
- name: diagram
dtype: int64
- name: graph
dtype: int64
- name: other_figure
dtype: int64
- name: tables
dtype: int64
- name: language
dtype: string
- name: subject
dtype: string
- name: image
dtype: image
splits:
- name: test
num_bytes: 186021336
num_examples: 1117
download_size: 190317242
dataset_size: 186021336
---

# ImageCLEF 2026 Multimodal Reasoning Multiple-Choice QA Dataset - Visual questions

## Introduction
The data is newly collected and annotated real-world data.
Participants are expected to send their model predictions to the leaderboard |on [AI4Media-Bench MCQ Visual](https://ai4media-bench.aimultimedialab.ro/competitions/12/). The `test` split for the final leaderboard is available.

## Test Distribution

### Language Distribution
The test split is distributed across several languages as follows:

| Language | Count |
| :--- | :---: |
| Bulgarian | 110 |
| Chinese | 342 |
| Croatian | 57 |
| English | 500 |
| Italian | 54 |
| Serbian | 54 |
| **Total** | **1117** |

### Graphical Distribution
The image-based test split contains various graphical elements:

| Graphical Feature | Count | Percentage |
| :--- | :---: | :---: |
| Diagrams | 644 | 57.65% |
| Graphs | 177 | 15.85% |
| Tables | 298 | 26.68% |
| Other Figures | 129 | 11.55% |