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.
Qwen3.5-122B-A10B from Alibaba Cloud / Qwen Team currently leads the SlakeVQA leaderboard with a score of 0.816 across 4 evaluated AI models.
What SlakeVQA measures
SlakeVQA is a multimodal benchmark that evaluates large language models on image to text, multimodal, reasoning, healthcare, and vision tasks. LLM Stats tracks 4 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.8, with the leader reaching 0.8.
Compare leaders on the best AI for image to text, best AI for multimodal, best AI for reasoning, best AI for healthcare and best AI for vision leaderboards.
Publication
- Paper
- SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering
- Authors
- Bo Liu, Li-Ming Zhan, Li Xu, Lin Ma, and 2 others
- Published
- arXiv
- 2102.09542
Abstract
Medical visual question answering (Med-VQA) has tremendous potential in healthcare. However, the development of this technology is hindered by the lacking of publicly-available and high-quality labeled datasets for training and evaluation. In this paper, we present a large bilingual dataset, SLAKE, with comprehensive semantic labels annotated by experienced physicians and a new structural medical knowledge base for Med-VQA. Besides, SLAKE includes richer modalities and covers more human body parts than the currently available dataset. We show that SLAKE can be used to facilitate the development and evaluation of Med-VQA systems. The dataset can be downloaded from http://www.med-vqa.com/slake.
Qwen3.5-122B-A10B leads with 81.6%, followed by Qwen3.5-27B at 80.0% and Qwen3.5-35B-A3B at 78.7%.
Progress Over Time
Interactive timeline showing model performance evolution on SlakeVQA
SlakeVQA Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 122B | 262K | $0.40 / $3.20 | ||
| 2 | Alibaba Cloud / Qwen Team | 27B | 262K | $0.30 / $2.40 | ||
| 3 | Alibaba Cloud / Qwen Team | 35B | 262K | $0.25 / $2.00 | ||
| 4 |  Google | 4B | — | — |
FAQ
Common questions about SlakeVQA.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions