# Diagnostic Accuracy on ReMeDi Source: [Diagnostic Accuracy on ReMeDi]() Collection index: [llms.txt]() Data updated: 2026-05-11T09:19:34.406Z Evaluation of model performance on the Diagnostic Accuracy task using the ReMeDi dataset, reporting accuracy across Neurology, Cardiology, and Nephrology sub-domains. 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 | Diagnostic Accuracy | | Dataset (including any stated split) | ReMeDi | | Metric | Accuracy (Neurology) | | Unit | SCALAR | | 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 - [Accuracy (Neurology)](): Higher is better; unit: SCALAR. - [Accuracy (Cardiology)](): Higher is better; unit: SCALAR. - [Accuracy (Nephrology)](): Higher is better; unit: SCALAR. - [Overall Accuracy](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy (Neurology) | Result date | Report paper | | --- | --- | --- | --- | | APP-DeepSeek-v3 | 3.9 | Not recorded | 68fa7ad61e209131cea856fd | | APP-QWen-72B | 3.43 | Not recorded | 68fa7ad61e209131cea856fd | | APP-DeepSeek-v3 | 3.33 | Not recorded | 68fa7ad61e209131cea856fd | | DeepSeek-v3 | 3.28 | Not recorded | 68fa7ad61e209131cea856fd | | Claude-3 | 3.23 | Not recorded | 68fa7ad61e209131cea856fd | | LLaMA-70B | 3.19 | Not recorded | 68fa7ad61e209131cea856fd | | GPT-4o | 3.1 | Not recorded | 68fa7ad61e209131cea856fd | | APP-QWen-72B | 3.09 | Not recorded | 68fa7ad61e209131cea856fd | | LLaMA-70B | 3.04 | Not recorded | 68fa7ad61e209131cea856fd | | DeepSeek-v3 | 3 | Not recorded | 68fa7ad61e209131cea856fd | | Claude-3 | 2.9 | Not recorded | 68fa7ad61e209131cea856fd | | QWen-72B | 2.86 | Not recorded | 68fa7ad61e209131cea856fd | | GPT-4o | 2.81 | Not recorded | 68fa7ad61e209131cea856fd | | QWen-72B | 2.47 | Not recorded | 68fa7ad61e209131cea856fd | ### APP-DeepSeek-v3 Accuracy (Neurology): 3.9. Result ID: 6a019f0c47f34ce924e3c330. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interaction Setting":"Multiple-Turn"}. This record does not assert independent reproduction. ### APP-QWen-72B Accuracy (Neurology): 3.43. Result ID: 6a019f0c47f34ce924e3c32c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interaction Setting":"Multiple-Turn"}. This record does not assert independent reproduction. ### APP-DeepSeek-v3 Accuracy (Neurology): 3.33. Result ID: 6a019f0c47f34ce924e3c32f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interaction Setting":"One-Shot"}. This record does not assert independent reproduction. ### DeepSeek-v3 Accuracy (Neurology): 3.28. Result ID: 6a019f0c47f34ce924e3c32e. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"Multiple-Turn"}. This record does not assert independent reproduction. ### Claude-3 Accuracy (Neurology): 3.23. Result ID: 6a019f0c47f34ce924e3c326. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"Multiple-Turn"}. This record does not assert independent reproduction. ### LLaMA-70B Accuracy (Neurology): 3.19. Result ID: 6a019f0c47f34ce924e3c324. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"Multiple-Turn"}. This record does not assert independent reproduction. ### GPT-4o Accuracy (Neurology): 3.1. Result ID: 6a019f0c47f34ce924e3c328. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"Multiple-Turn"}. This record does not assert independent reproduction. ### APP-QWen-72B Accuracy (Neurology): 3.09. Result ID: 6a019f0c47f34ce924e3c32b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Interaction Setting":"One-Shot"}. This record does not assert independent reproduction. ### LLaMA-70B Accuracy (Neurology): 3.04. Result ID: 6a019f0c47f34ce924e3c323. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"One-Shot"}. This record does not assert independent reproduction. ### DeepSeek-v3 Accuracy (Neurology): 3. Result ID: 6a019f0c47f34ce924e3c32d. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"One-Shot"}. This record does not assert independent reproduction. ### Claude-3 Accuracy (Neurology): 2.9. Result ID: 6a019f0c47f34ce924e3c325. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"One-Shot"}. This record does not assert independent reproduction. ### QWen-72B Accuracy (Neurology): 2.86. Result ID: 6a019f0c47f34ce924e3c32a. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"Multiple-Turn"}. This record does not assert independent reproduction. ### GPT-4o Accuracy (Neurology): 2.81. Result ID: 6a019f0c47f34ce924e3c327. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"One-Shot"}. This record does not assert independent reproduction. ### QWen-72B Accuracy (Neurology): 2.47. Result ID: 6a019f0c47f34ce924e3c329. [Reporting paper]() Recorded evaluation configuration: {"Interaction Setting":"One-Shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.