# Medical Diagnosis on Step-CoT (test) Source: [Medical Diagnosis on Step-CoT (test)]() Collection index: [llms.txt]() Data updated: 2026-03-17T08:52:56.509Z Evaluation of model performance on the test split of the Step-CoT dataset for general Medical Diagnosis capabilities, measured by Accuracy, mAUC, Sensitivity, and Specificity. 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 Diagnosis | | Dataset (including any stated split) | Step-CoT (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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. - [mAUC](): Higher is better; unit: PERCENT. - [Sensitivity](): Higher is better; unit: PERCENT. - [Specificity](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Ours (Teacher) | 78.3 | Not recorded | 69b8dff20636e5bf4afbe8c0 | | Ours (Student) | 77.5 | Not recorded | 69b8dff20636e5bf4afbe8c0 | | biomedclip | 69.3 | Not recorded | 69b8dff20636e5bf4afbe8c0 | | ALBEF | 68.1 | Not recorded | 69b8dff20636e5bf4afbe8c0 | | BLIP | 66.4 | Not recorded | 69b8dff20636e5bf4afbe8c0 | | CLIP | 64.7 | Not recorded | 69b8dff20636e5bf4afbe8c0 | | FLAVA | 62.5 | Not recorded | 69b8dff20636e5bf4afbe8c0 | | VisualBERT | 56.2 | Not recorded | 69b8dff20636e5bf4afbe8c0 | | LLaVA-Med | 42.7 | Not recorded | 69b8dff20636e5bf4afbe8c0 | | Med-Flamingo | 30.1 | Not recorded | 69b8dff20636e5bf4afbe8c0 | ### Ours (Teacher) Accuracy: 78.3. Result ID: 69b9165a47f34ce924a1c3e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"Proposed framework","Step-CoT":"Enabled"}. This record does not assert independent reproduction. ### Ours (Student) Accuracy: 77.5. Result ID: 69b9165a47f34ce924a1c3e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"Proposed framework","Step-CoT":"Enabled"}. This record does not assert independent reproduction. ### biomedclip Accuracy: 69.3. Result ID: 69b9165a47f34ce924a1c3df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"Visual foundation model","Step-CoT":"Enabled"}. This record does not assert independent reproduction. ### ALBEF Accuracy: 68.1. Result ID: 69b9165a47f34ce924a1c3dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"type":"Visual foundation model","Step-CoT":"Enabled"}. This record does not assert independent reproduction. ### BLIP Accuracy: 66.4. Result ID: 69b9165a47f34ce924a1c3dd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"type":"Visual foundation model","Step-CoT":"Enabled"}. This record does not assert independent reproduction. ### CLIP Accuracy: 64.7. Result ID: 69b9165a47f34ce924a1c3db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"type":"Visual foundation model","Step-CoT":"Enabled"}. This record does not assert independent reproduction. ### FLAVA Accuracy: 62.5. Result ID: 69b9165a47f34ce924a1c3de. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"type":"Visual foundation model","Step-CoT":"Enabled"}. This record does not assert independent reproduction. ### VisualBERT Accuracy: 56.2. Result ID: 69b9165a47f34ce924a1c3da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"Visual foundation model","Step-CoT":"Enabled"}. This record does not assert independent reproduction. ### LLaVA-Med Accuracy: 42.7. Result ID: 69b9165a47f34ce924a1c3d8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"type":"LVLM","Step-CoT":"Disabled"}. This record does not assert independent reproduction. ### Med-Flamingo Accuracy: 30.1. Result ID: 69b9165a47f34ce924a1c3d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"LVLM","Step-CoT":"Disabled"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.