multimodal benchmark
SlakeVQA
A semantically-labeled knowledge-enhanced dataset for medical visual question answering. Contains 642 radiology images (CT scans, MRI scans, X-rays) covering five body parts and 14,028 bilingual English-Chinese question-answer pairs annotated by experienced physicians. Features comprehensive semantic labels and a structural medical knowledge base with both vision-only and knowledge-based questions requiring external medical knowledge reasoning.
Updated Aug 7, 2026
Published models4
Registry coverage4
MetricScore
EvidenceB
SlakeVQA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 81.6% | 100.0% | 4 | C | |
| 2 | AC | 80.0% | 66.7% | 4 | C | |
| 3 | AC | 78.7% | 33.3% | 4 | C | |
| 4 | GO | 62.3% | 0.0% | 4 | C |
Score distribution
Top published rows on the benchmark's original scale.
SlakeVQA highlights
The top published results on this benchmark's own scale.
What is SlakeVQA?
Definition and scoring fields from the benchmark registry.
A semantically-labeled knowledge-enhanced dataset for medical visual question answering. Contains 642 radiology images (CT scans, MRI scans, X-rays) covering five body parts and 14,028 bilingual English-Chinese question-answer pairs annotated by experienced physicians. Features comprehensive semantic labels and a structural medical knowledge base with both vision-only and knowledge-based questions requiring external medical knowledge reasoning.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SlakeVQA
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- slakevqa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SlakeVQA.
Which model scores highest on SlakeVQA?
Qwen3.5-122B-A10B is currently ranked first with 81.6%.
What does SlakeVQA measure?
A semantically-labeled knowledge-enhanced dataset for medical visual question answering. Contains 642 radiology images (CT scans, MRI scans, X-rays) covering five body parts and 14,028 bilingual English-Chinese question-answer pairs annotated by experienced physicians. Features comprehensive semantic labels and a structural medical knowledge base with both vision-only and knowledge-based questions requiring external medical knowledge reasoning.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.