# Medical Visual Question Answering (Multiple-choice) on MedXQA OOD Source: [Medical Visual Question Answering (Multiple-choice) on MedXQA OOD]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:11:30.732Z Evaluation of model performance on the Out-of-Distribution (OOD) split of the MedXQA dataset for Medical Visual Question Answering, focusing on multiple-choice questions. 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) | MedXQA OOD | | 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 | | --- | --- | --- | --- | | Lingshu-7B | 26.5 | Not recorded | 69d884327d0172140ec77b60 | | MedVR | 26.4 | Not recorded | 69d884327d0172140ec77b60 | | Qwen2.5-VL-32B | 24.5 | Not recorded | 69d884327d0172140ec77b60 | | InternVL3-14B | 23.1 | Not recorded | 69d884327d0172140ec77b60 | | Qwen2.5-VL-7B | 22.3 | Not recorded | 69d884327d0172140ec77b60 | | HuatuoGPT-V-7B | 22.3 | Not recorded | 69d884327d0172140ec77b60 | | InternVL3-8B | 22.1 | Not recorded | 69d884327d0172140ec77b60 | | Med-R1-2B | 21.1 | Not recorded | 69d884327d0172140ec77b60 | | InternVL2.5-8B | 21 | Not recorded | 69d884327d0172140ec77b60 | | LLaVA-Med-7B | 20.3 | Not recorded | 69d884327d0172140ec77b60 | | MedVLM-R1-2B | 20.1 | Not recorded | 69d884327d0172140ec77b60 | | MedGemma-4B | 15.4 | Not recorded | 69d884327d0172140ec77b60 | ### Lingshu-7B Accuracy: 26.5. Result ID: 69d8bebb47f34ce924c1d945. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### MedVR Accuracy: 26.4. Result ID: 69d8bebb47f34ce924c1d946. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"Out-of-domain","Backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL-32B Accuracy: 24.5. Result ID: 69d8bebb47f34ce924c1d93c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### InternVL3-14B Accuracy: 23.1. Result ID: 69d8bebb47f34ce924c1d93f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy: 22.3. Result ID: 69d8bebb47f34ce924c1d93b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### HuatuoGPT-V-7B Accuracy: 22.3. Result ID: 69d8bebb47f34ce924c1d944. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### InternVL3-8B Accuracy: 22.1. Result ID: 69d8bebb47f34ce924c1d93e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### Med-R1-2B Accuracy: 21.1. Result ID: 69d8bebb47f34ce924c1d940. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### InternVL2.5-8B Accuracy: 21. Result ID: 69d8bebb47f34ce924c1d93d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"General-Purpose VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### LLaVA-Med-7B Accuracy: 20.3. Result ID: 69d8bebb47f34ce924c1d943. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### MedVLM-R1-2B Accuracy: 20.1. Result ID: 69d8bebb47f34ce924c1d941. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. ### MedGemma-4B Accuracy: 15.4. Result ID: 69d8bebb47f34ce924c1d942. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical-Specific VLMs","Evaluation Protocol":"Out-of-domain"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.