# Pathology Visual Question Answering on PathMMU (val) Source: [Pathology Visual Question Answering on PathMMU (val)]() Collection index: [llms.txt]() Data updated: 2026-06-17T06:53:03.773Z Evaluation of model performance on the validation split (val) of the PathMMU dataset specifically for Pathology Visual Question Answering tasks. 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 | Pathology Visual Question Answering | | Dataset (including any stated split) | PathMMU (val) | | Metric | Overall Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Accuracy | Result date | Report paper | | --- | --- | --- | --- | | ScaleReasoner-R1 | 62.4 | Not recorded | 6a322a37d33dfb23e783ec35 | | Patho-R1 | 62.3 | Not recorded | 6a322a37d33dfb23e783ec35 | | CLOVER | 53.1 | Not recorded | 6a322a37d33dfb23e783ec35 | | Lingshu-7B | 51.9 | Not recorded | 6a322a37d33dfb23e783ec35 | | GPT-4V | 49.3 | Not recorded | 6a322a37d33dfb23e783ec35 | | SFT + RL | 48.3 | Not recorded | 6a322a37d33dfb23e783ec35 | | SFT | 47.8 | Not recorded | 6a322a37d33dfb23e783ec35 | | Qwen2.5-VL-7B | 44.3 | Not recorded | 6a322a37d33dfb23e783ec35 | | HuatuoGPT-V-7B | 43.2 | Not recorded | 6a322a37d33dfb23e783ec35 | | Gemini Pro Vision | 41.9 | Not recorded | 6a322a37d33dfb23e783ec35 | | Quilt-LLaVA | 33.8 | Not recorded | 6a322a37d33dfb23e783ec35 | | Frequent Choice | 27.5 | Not recorded | 6a322a37d33dfb23e783ec35 | | Random Choice | 24.6 | Not recorded | 6a322a37d33dfb23e783ec35 | | LLaVA-Med-7B | 17.5 | Not recorded | 6a322a37d33dfb23e783ec35 | ### ScaleReasoner-R1 Overall Accuracy: 62.4. Result ID: 6a324436fbc373592c2f3171. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Pathological VLM","Backbone":"PathoR1-7B"}. This record does not assert independent reproduction. ### Patho-R1 Overall Accuracy: 62.3. Result ID: 6a324436fbc373592c2f3170. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Pathological VLM","Backbone":"PathoR1-7B"}. This record does not assert independent reproduction. ### CLOVER Overall Accuracy: 53.1. Result ID: 6a324436fbc373592c2f316f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Pathological VLM"}. This record does not assert independent reproduction. ### Lingshu-7B Overall Accuracy: 51.9. Result ID: 6a324436fbc373592c2f316d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Medical VLM","Parameters":"7B"}. This record does not assert independent reproduction. ### GPT-4V Overall Accuracy: 49.3. Result ID: 6a324436fbc373592c2f316a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"General domain VLM","Source":"PathMMU paper"}. This record does not assert independent reproduction. ### SFT + RL Overall Accuracy: 48.3. Result ID: 6a324436fbc373592c2f3173. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Ablation Study","Backbone":"PathoR1-7B"}. This record does not assert independent reproduction. ### SFT Overall Accuracy: 47.8. Result ID: 6a324436fbc373592c2f3172. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Ablation Study","Backbone":"PathoR1-7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Overall Accuracy: 44.3. Result ID: 6a324436fbc373592c2f3168. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"General domain VLM","Parameters":"7B"}. This record does not assert independent reproduction. ### HuatuoGPT-V-7B Overall Accuracy: 43.2. Result ID: 6a324436fbc373592c2f316c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Medical VLM","Parameters":"7B"}. This record does not assert independent reproduction. ### Gemini Pro Vision Overall Accuracy: 41.9. Result ID: 6a324436fbc373592c2f3169. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"General domain VLM","Source":"PathMMU paper"}. This record does not assert independent reproduction. ### Quilt-LLaVA Overall Accuracy: 33.8. Result ID: 6a324436fbc373592c2f316e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Pathological VLM"}. This record does not assert independent reproduction. ### Frequent Choice Overall Accuracy: 27.5. Result ID: 6a324436fbc373592c2f3167. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Baseline","Source":"PathMMU paper"}. This record does not assert independent reproduction. ### Random Choice Overall Accuracy: 24.6. Result ID: 6a324436fbc373592c2f3166. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Baseline","Source":"PathMMU paper"}. This record does not assert independent reproduction. ### LLaVA-Med-7B Overall Accuracy: 17.5. Result ID: 6a324436fbc373592c2f316b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Medical VLM","Parameters":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.