BELO Benchmark for Evaluating Language Models in Ophthalmology
Expert-curated ophthalmology multiple-choice benchmark with rationales, assembled for held-out language-model evaluation.
At a glance
| Field | Value |
|---|---|
| Short name | belo |
| Full name | BELO Benchmark for Evaluating Language Models in Ophthalmology |
| Primary category | text |
| Contained modalities | text |
| Tasks | question_answering, evaluation, reasoning |
| Samples | 900 |
| Classes | Not reported (Not reported) |
| Splits | all |
| Size | Not reported |
| Source-stated terms | Unknown; mixed upstream question-bank terms |
| Normalized terms | unknown |
| Descriptive screening label | Unknown or unclear; do not assume permission |
| Terms scope | mixed_components |
| Access friction | author_contact |
| Route backend | Manual (upstream-gated) |
| Availability | available (checked 2026-07-21) |
| Acquisition support | manual_access_blocked |
| Legacy sample-loader status | Metadata and access only |
Notes
The 900 questions aggregate BCSC, BioASQ, MedMCQA, MedQA, and PubMedQA sources. The project page instructs users to request the held-out benchmark by email; verify every applicable source term.
Access preflight and acquisition
- CLI
- Python
# This route requires upstream human action; no transfer starts.
eyehub download belo --data-dir ./data --dry-run --json
# Follow the official instructions shown by preflight.
from eyedatahub.acquisition import preflight_dataset
from eyedatahub.datasets.registry import REGISTRY
ds = REGISTRY.get_dataset('belo')
print(preflight_dataset(ds, './data')) # returns manual_access_blocked
Upstream page: belo-dataset.vercel.app
Source-term evidence: belo-dataset.vercel.app
Loader status
This catalog record provides metadata and access instructions, but it does not yet include a standard DatasetSample loader. Inspect the source file structure or contribute a loader before using it in a training pipeline.
Citation
- BibTeX
- Plain text
@misc{belo,
title = { BELO Benchmark for Evaluating Language Models in Ophthalmology },
note = { BELO: A Benchmark for Evaluation of Language Models in Ophthalmology. Ophthalmology Science. 2025:101050. doi:10.1016/j.xops.2025.101050 },
year = { 2025 },
url = { https://belo-dataset.vercel.app/ },
}
BELO: A Benchmark for Evaluation of Language Models in Ophthalmology. Ophthalmology Science. 2025:101050. doi:10.1016/j.xops.2025.101050
Source-stated terms
- Raw source string: Unknown; mixed upstream question-bank terms
- Normalized category:
unknown - Apparent scope:
mixed_components - Descriptive screening label: Unknown or unclear; do not assume permission
⚠️ Source-stated terms, scope, and normalized labels are curation metadata, not legal advice or a permission finding. Review the current official source before transfer or reuse.
Related datasets with shared modalities
- fundus_cc_2_5m: Fundus-CC-2.5M Text Corpus (2,500,000 records,
unknown) - ocular_chat_vqa: OcularChat-VQA: AREDS-Derived Patient-Physician Dialogue Dataset (844,000 records,
cc-by-nc-sa) - ophora: Ophora-160K: Ophthalmic Surgical Video Instruction Dataset (160,185 records,
unknown) - fundus_105k: Fundus-105K Text Dataset (105,000 records,
unknown) - eyecare_100k: Eyecare-100K: Multimodal Ophthalmology VQA Corpus (102,000 records,
unknown) - angioreport: AngioReport Fundus Angiography Report Dataset (55,361 records,
unknown) - ophthalmology_mcqa_v3: Ophthalmology-MCQA-v3 (51,745 records,
unknown) - ophthalmology_eqa_v3: Ophthalmology-EQA-v3 (49,300 records,
unknown)