# Visual Question Answering (Closed-ended) on VQA-RAD closed-ended Source: [Visual Question Answering (Closed-ended) on VQA-RAD closed-ended]() Collection index: [llms.txt]() Data updated: 2026-06-08T06:46:02.120Z Evaluation of model performance on the closed-ended subset of the VQA-RAD dataset for Visual Question Answering, reporting Accuracy, F1, Precision, and Recall. 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 | Visual Question Answering (Closed-ended) | | Dataset (including any stated split) | VQA-RAD closed-ended | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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. - [F1 Score](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | BiasCareVL | 82.5 | Not recorded | 69e704767d0172140ec7ec02 | | MEDSIGHT | 82.3 | Not recorded | 6a264c8f90966ade919bea04 | | BioMedGPT | 81.3 | Not recorded | 69e704767d0172140ec7ec02 | | HuatuoGPT-Vision 7B | 76.8 | Not recorded | 6a264c8f90966ade919bea04 | | ExGra-Med | 75.2 | Not recorded | 6a264c8f90966ade919bea04 | | LLaVA-Med 1.5 | 74.4 | Not recorded | 6a264c8f90966ade919bea04 | | HuaTuoGPT-Vision-34B | 68.1 | Not recorded | 69e704767d0172140ec7ec02 | | HuaTuoGPT-Vision-7B | 67.5 | Not recorded | 69e704767d0172140ec7ec02 | | MedPLIB-7B | 66.7 | Not recorded | 69e704767d0172140ec7ec02 | | MIMO | 58.8 | Not recorded | 69e704767d0172140ec7ec02 | | RadFM | 50.6 | Not recorded | 69e704767d0172140ec7ec02 | | DeepSeek-VL2-tiny | 48.8 | Not recorded | 69e704767d0172140ec7ec02 | | DeepSeek-VL2-small | 48 | Not recorded | 69e704767d0172140ec7ec02 | | Qwen-VL-Chat | 47 | Not recorded | 69e704767d0172140ec7ec02 | | Med-Flamingo | 45.4 | Not recorded | 69e704767d0172140ec7ec02 | | Qwen-VL2.5-3B-Instruct | 26.6 | Not recorded | 69e704767d0172140ec7ec02 | ### BiasCareVL Accuracy: 82.5. Result ID: 69e734c147f34ce924cd65de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MEDSIGHT Accuracy: 82.3. Result ID: 6a266525fbc373592c2285f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning protocol":"LoRA","LoRA rank":"32"}. This record does not assert independent reproduction. ### BioMedGPT Accuracy: 81.3. Result ID: 69e734c147f34ce924cd65d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2024"}. This record does not assert independent reproduction. ### HuatuoGPT-Vision 7B Accuracy: 76.8. Result ID: 6a266525fbc373592c2285ef. [Reporting paper]() Recorded evaluation configuration: {"Fine-tuning protocol":"LoRA","LoRA rank":"32"}. This record does not assert independent reproduction. ### ExGra-Med Accuracy: 75.2. Result ID: 6a266525fbc373592c2285f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning protocol":"LoRA","LoRA rank":"32"}. This record does not assert independent reproduction. ### LLaVA-Med 1.5 Accuracy: 74.4. Result ID: 6a266525fbc373592c2285ee. [Reporting paper]() Recorded evaluation configuration: {"Fine-tuning protocol":"LoRA","LoRA rank":"32"}. This record does not assert independent reproduction. ### HuaTuoGPT-Vision-34B Accuracy: 68.1. Result ID: 69e734c147f34ce924cd65d6. [Reporting paper]() Recorded evaluation configuration: {"Year":"2024","Parameters":"34B"}. This record does not assert independent reproduction. ### HuaTuoGPT-Vision-7B Accuracy: 67.5. Result ID: 69e734c147f34ce924cd65d5. [Reporting paper]() Recorded evaluation configuration: {"Year":"2024","Parameters":"7B"}. This record does not assert independent reproduction. ### MedPLIB-7B Accuracy: 66.7. Result ID: 69e734c147f34ce924cd65dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2025","Parameters":"7B"}. This record does not assert independent reproduction. ### MIMO Accuracy: 58.8. Result ID: 69e734c147f34ce924cd65dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2025"}. This record does not assert independent reproduction. ### RadFM Accuracy: 50.6. Result ID: 69e734c147f34ce924cd65db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2025"}. This record does not assert independent reproduction. ### DeepSeek-VL2-tiny Accuracy: 48.8. Result ID: 69e734c147f34ce924cd65d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2025"}. This record does not assert independent reproduction. ### DeepSeek-VL2-small Accuracy: 48. Result ID: 69e734c147f34ce924cd65da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2025"}. This record does not assert independent reproduction. ### Qwen-VL-Chat Accuracy: 47. Result ID: 69e734c147f34ce924cd65d4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2023"}. This record does not assert independent reproduction. ### Med-Flamingo Accuracy: 45.4. Result ID: 69e734c147f34ce924cd65d3. [Reporting paper]() Recorded evaluation configuration: {"Year":"2023"}. This record does not assert independent reproduction. ### Qwen-VL2.5-3B-Instruct Accuracy: 26.6. Result ID: 69e734c147f34ce924cd65d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2025","Parameters":"3B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.