# Multimodal Medical Understanding on MMMU Source: [Multimodal Medical Understanding on MMMU]() Collection index: [llms.txt]() Data updated: 2026-04-29T08:00:56.702Z Evaluation of model performance on the MMMU dataset, specifically focusing on the medical domain subset or specialized medical reasoning tasks, measured by 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 | Multimodal Medical Understanding | | Dataset (including any stated split) | MMMU | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 | | --- | --- | --- | --- | | Ours-7B | 73.77 | Not recorded | 69f190b655a3c32af89fbc0e | | Ours (7B) | 62.94 | Not recorded | 69a66c1a2d603e6de3e3ce72 | | QoQ-Med-7B | 61.18 | Not recorded | 69a66c1a2d603e6de3e3ce72 | | InternVL3-8B | 58 | Not recorded | 69f190b655a3c32af89fbc0e | | OctoMed-7B | 56.47 | Not recorded | 69a66c1a2d603e6de3e3ce72 | | Qwen2.5-VL-7B | 56 | Not recorded | 69f190b655a3c32af89fbc0e | | Qwen2.5-VL-7B-Instruct | 55.29 | Not recorded | 69a66c1a2d603e6de3e3ce72 | | MedVLThinker-7B | 54.12 | Not recorded | 69a66c1a2d603e6de3e3ce72 | | Lingshu-7B | 54 | Not recorded | 69f190b655a3c32af89fbc0e | | HuatuoGPT-V-7B | 47.3 | Not recorded | 69f190b655a3c32af89fbc0e | | Med-R1-2B | 41.18 | Not recorded | 69a66c1a2d603e6de3e3ce72 | | BioMediX2-8B | 39.8 | Not recorded | 69f190b655a3c32af89fbc0e | | MedVLM-R1-2B | 39.41 | Not recorded | 69a66c1a2d603e6de3e3ce72 | | LLaVa1.6-7B | 36 | Not recorded | 69f190b655a3c32af89fbc0e | | LLaVa-Med-7B | 29.3 | Not recorded | 69f190b655a3c32af89fbc0e | ### Ours-7B Accuracy: 73.77. Result ID: 69f1baa347f34ce924d80abe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical Models"}. This record does not assert independent reproduction. ### Ours (7B) Accuracy: 62.94. Result ID: 69a836846dbb7075b94ec323. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### QoQ-Med-7B Accuracy: 61.18. Result ID: 69a836846dbb7075b94ec31e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### InternVL3-8B Accuracy: 58. Result ID: 69f1baa347f34ce924d80ab9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### OctoMed-7B Accuracy: 56.47. Result ID: 69a836846dbb7075b94ec320. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy: 56. Result ID: 69f1baa347f34ce924d80ab8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Instruct Accuracy: 55.29. Result ID: 69a836846dbb7075b94ec31d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### MedVLThinker-7B Accuracy: 54.12. Result ID: 69a836846dbb7075b94ec31f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### Lingshu-7B Accuracy: 54. Result ID: 69f1baa347f34ce924d80abd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical Models"}. This record does not assert independent reproduction. ### HuatuoGPT-V-7B Accuracy: 47.3. Result ID: 69f1baa347f34ce924d80abc. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Medical Models"}. This record does not assert independent reproduction. ### Med-R1-2B Accuracy: 41.18. Result ID: 69a836846dbb7075b94ec322. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction. ### BioMediX2-8B Accuracy: 39.8. Result ID: 69f1baa347f34ce924d80abb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Medical Models"}. This record does not assert independent reproduction. ### MedVLM-R1-2B Accuracy: 39.41. Result ID: 69a836846dbb7075b94ec321. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction. ### LLaVa1.6-7B Accuracy: 36. Result ID: 69f1baa347f34ce924d80ab7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### LLaVa-Med-7B Accuracy: 29.3. Result ID: 69f1baa347f34ce924d80aba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Medical Models"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.