# Multiple-choice Medical Visual Question Answering on PMC-VQA OOD Source: [Multiple-choice Medical Visual Question Answering on PMC-VQA OOD]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:11:30.703Z Evaluation of model performance on the Out-of-Distribution (OOD) subset of the PMC-VQA dataset, specifically focusing on multiple-choice question answering. 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) | PMC-VQA 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 | 54.3 | Not recorded | 69d884327d0172140ec77b60 | | MedVR | 54.3 | Not recorded | 69d884327d0172140ec77b60 | | Qwen2.5-VL-32B | 54.1 | Not recorded | 69d884327d0172140ec77b60 | | InternVL3-14B | 54.1 | Not recorded | 69d884327d0172140ec77b60 | | InternVL3-8B | 53.8 | Not recorded | 69d884327d0172140ec77b60 | | HuatuoGPT-V-7B | 53.3 | Not recorded | 69d884327d0172140ec77b60 | | InternVL2.5-8B | 51.3 | Not recorded | 69d884327d0172140ec77b60 | | Qwen2.5-VL-7B | 51.2 | Not recorded | 69d884327d0172140ec77b60 | | MedGemma-4B | 49.9 | Not recorded | 69d884327d0172140ec77b60 | | MedVLM-R1-2B | 47.5 | Not recorded | 69d884327d0172140ec77b60 | | Med-R1-2B | 47.4 | Not recorded | 69d884327d0172140ec77b60 | | LLaVA-Med-7B | 30.5 | Not recorded | 69d884327d0172140ec77b60 | ### Lingshu-7B Accuracy: 54.3. Result ID: 69d8bebb47f34ce924c1d939. [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: 54.3. Result ID: 69d8bebb47f34ce924c1d93a. [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: 54.1. Result ID: 69d8bebb47f34ce924c1d930. [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: 54.1. Result ID: 69d8bebb47f34ce924c1d933. [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. ### InternVL3-8B Accuracy: 53.8. Result ID: 69d8bebb47f34ce924c1d932. [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: 53.3. Result ID: 69d8bebb47f34ce924c1d938. [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: 51.3. Result ID: 69d8bebb47f34ce924c1d931. [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. ### Qwen2.5-VL-7B Accuracy: 51.2. Result ID: 69d8bebb47f34ce924c1d92f. [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. ### MedGemma-4B Accuracy: 49.9. Result ID: 69d8bebb47f34ce924c1d936. [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. ### MedVLM-R1-2B Accuracy: 47.5. Result ID: 69d8bebb47f34ce924c1d935. [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. ### Med-R1-2B Accuracy: 47.4. Result ID: 69d8bebb47f34ce924c1d934. [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. ### LLaVA-Med-7B Accuracy: 30.5. Result ID: 69d8bebb47f34ce924c1d937. [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. Page 1 of 1. This is an index page, not the full collection.