# Medical Visual Question Answering (Multiple-choice) on OMVQA (test) Source: [Medical Visual Question Answering (Multiple-choice) on OMVQA (test)]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:11:30.678Z Evaluation of model performance on the test split of the OMVQA dataset for multiple-choice medical visual question answering, reporting accuracy. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Medical Visual Question Answering (Multiple-choice) | | Dataset (including any stated split) | OMVQA official (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MedVR | 96.8 | Not recorded | 69d884327d0172140ec77b60 | | Lingshu-7B | 84.2 | Not recorded | 69d884327d0172140ec77b60 | | InternVL2.5-8B | 83.9 | Not recorded | 69d884327d0172140ec77b60 | | InternVL3-14B | 81.9 | Not recorded | 69d884327d0172140ec77b60 | | InternVL3-8B | 81.4 | Not recorded | 69d884327d0172140ec77b60 | | HuatuoGPT-V-7B | 80.1 | Not recorded | 69d884327d0172140ec77b60 | | Med-R1-2B | 77.3 | Not recorded | 69d884327d0172140ec77b60 | | MedGemma-4B | 70.5 | Not recorded | 69d884327d0172140ec77b60 | | Qwen2.5-VL-32B | 69.9 | Not recorded | 69d884327d0172140ec77b60 | | Qwen2.5-VL-7B | 59 | Not recorded | 69d884327d0172140ec77b60 | | MedVLM-R1-2B | 57.4 | Not recorded | 69d884327d0172140ec77b60 | | LLaVA-Med-7B | 29.3 | Not recorded | 69d884327d0172140ec77b60 | ### MedVR Accuracy: 96.8. Result ID: 69d8bebb47f34ce924c1d92e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"In-domain","Backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### Lingshu-7B Accuracy: 84.2. Result ID: 69d8bebb47f34ce924c1d92d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### InternVL2.5-8B Accuracy: 83.9. Result ID: 69d8bebb47f34ce924c1d925. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### InternVL3-14B Accuracy: 81.9. Result ID: 69d8bebb47f34ce924c1d927. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### InternVL3-8B Accuracy: 81.4. Result ID: 69d8bebb47f34ce924c1d926. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### HuatuoGPT-V-7B Accuracy: 80.1. Result ID: 69d8bebb47f34ce924c1d92c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### Med-R1-2B Accuracy: 77.3. Result ID: 69d8bebb47f34ce924c1d928. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### MedGemma-4B Accuracy: 70.5. Result ID: 69d8bebb47f34ce924c1d92a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### Qwen2.5-VL-32B Accuracy: 69.9. Result ID: 69d8bebb47f34ce924c1d924. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy: 59. Result ID: 69d8bebb47f34ce924c1d923. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### MedVLM-R1-2B Accuracy: 57.4. Result ID: 69d8bebb47f34ce924c1d929. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### LLaVA-Med-7B Accuracy: 29.3. Result ID: 69d8bebb47f34ce924c1d92b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.