# Medical Reasoning on DeepTumorVQA Source: [Medical Reasoning on DeepTumorVQA]() Collection index: [llms.txt]() Data updated: 2026-03-27T12:51:52.151Z Evaluation of medical reasoning capabilities on the DeepTumorVQA dataset, focusing on specific diagnostic tasks such as fatty liver assessment, lesion classification, and pancreatic tumor staging/resectability. 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 Reasoning | | Dataset (including any stated split) | DeepTumorVQA | | Metric | Fatty Liver Assessment | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Fatty Liver Assessment](): Higher is better; unit: PERCENT. - [Lesion Type Classification Accuracy](): Higher is better; unit: PERCENT. - [Pancreatic Cyst Resectability Score](): Higher is better; unit: PERCENT. - [Pancreatic Lesion Resectability Score](): Higher is better; unit: PERCENT. - [Pancreatic Steatosis Assessment](): Higher is better; unit: PERCENT. - [Pancreatic Tumor Staging Accuracy](): Higher is better; unit: PERCENT. - [Average Performance](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Fatty Liver Assessment | Result date | Report paper | | --- | --- | --- | --- | | Photon | 77.3 | Not recorded | 69c60efd0636e5bf4afc84c6 | | RadFM | 57.8 | Not recorded | 69c60efd0636e5bf4afc84c6 | | Photon | 55.8 | Not recorded | 69c60efd0636e5bf4afc84c6 | | CT-CHAT | 48.7 | Not recorded | 69c60efd0636e5bf4afc84c6 | | Merlin | 48.1 | Not recorded | 69c60efd0636e5bf4afc84c6 | | M3D-L2 | 48.1 | Not recorded | 69c60efd0636e5bf4afc84c6 | | CT-CHAT | 48.1 | Not recorded | 69c60efd0636e5bf4afc84c6 | | RadFM | 48.1 | Not recorded | 69c60efd0636e5bf4afc84c6 | | M3D-L2 | 46.1 | Not recorded | 69c60efd0636e5bf4afc84c6 | | M3D-P3 | 45.5 | Not recorded | 69c60efd0636e5bf4afc84c6 | | M3D-P3 | 39.6 | Not recorded | 69c60efd0636e5bf4afc84c6 | | Rand | 33.3 | Not recorded | 69c60efd0636e5bf4afc84c6 | | Merlin | 31.8 | Not recorded | 69c60efd0636e5bf4afc84c6 | ### Photon Fatty Liver Assessment: 77.3. Result ID: 69c67d5847f34ce924b06d7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Mode":"Free-text","Model Parameters":"3B"}. This record does not assert independent reproduction. ### RadFM Fatty Liver Assessment: 57.8. Result ID: 69c67d5847f34ce924b06d7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Mode":"Free-text","Model Parameters":"13B"}. This record does not assert independent reproduction. ### Photon Fatty Liver Assessment: 55.8. Result ID: 69c67d5847f34ce924b06d7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Mode":"Multi-choice","Model Parameters":"3B"}. This record does not assert independent reproduction. ### CT-CHAT Fatty Liver Assessment: 48.7. Result ID: 69c67d5847f34ce924b06d7a. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Mode":"Free-text","Model Parameters":"7B"}. This record does not assert independent reproduction. ### Merlin Fatty Liver Assessment: 48.1. Result ID: 69c67d5847f34ce924b06d74. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Mode":"Free-text","Model Parameters":"7B"}. This record does not assert independent reproduction. ### M3D-L2 Fatty Liver Assessment: 48.1. Result ID: 69c67d5847f34ce924b06d76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Mode":"Free-text","Model Parameters":"7B"}. This record does not assert independent reproduction. ### CT-CHAT Fatty Liver Assessment: 48.1. Result ID: 69c67d5847f34ce924b06d79. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Mode":"Multi-choice","Model Parameters":"7B"}. This record does not assert independent reproduction. ### RadFM Fatty Liver Assessment: 48.1. Result ID: 69c67d5847f34ce924b06d7b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Mode":"Multi-choice","Model Parameters":"13B"}. This record does not assert independent reproduction. ### M3D-L2 Fatty Liver Assessment: 46.1. Result ID: 69c67d5847f34ce924b06d75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Mode":"Multi-choice","Model Parameters":"7B"}. This record does not assert independent reproduction. ### M3D-P3 Fatty Liver Assessment: 45.5. Result ID: 69c67d5847f34ce924b06d77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Mode":"Multi-choice","Model Parameters":"4B"}. This record does not assert independent reproduction. ### M3D-P3 Fatty Liver Assessment: 39.6. Result ID: 69c67d5847f34ce924b06d78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Mode":"Free-text","Model Parameters":"4B"}. This record does not assert independent reproduction. ### Rand Fatty Liver Assessment: 33.3. Result ID: 69c67d5847f34ce924b06d72. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Mode":"Multi-choice"}. This record does not assert independent reproduction. ### Merlin Fatty Liver Assessment: 31.8. Result ID: 69c67d5847f34ce924b06d73. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Mode":"Multi-choice","Model Parameters":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.