# Clinical Reasoning on MedR-Bench Diagnosis Source: [Clinical Reasoning on MedR-Bench Diagnosis]() Collection index: [llms.txt]() Data updated: 2026-03-24T17:08:17.097Z Evaluation of model performance on the Clinical Reasoning task using the MedR-Bench Diagnosis dataset, reporting 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 | Clinical Reasoning | | Dataset (including any stated split) | MedR-Bench Diagnosis | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 | | --- | --- | --- | --- | | GSEM | 94.22 | Not recorded | 69c21ad30636e5bf4afc4d18 | | A-Mem | 93.62 | Not recorded | 69c21ad30636e5bf4afc4d18 | | FLEX | 93.31 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Naïve RAG | 92.4 | Not recorded | 69c21ad30636e5bf4afc4d18 | | ReMe | 91.49 | Not recorded | 69c21ad30636e5bf4afc4d18 | | GSEM | 91.49 | Not recorded | 69c21ad30636e5bf4afc4d18 | | GraphRAG | 90.27 | Not recorded | 69c21ad30636e5bf4afc4d18 | | ReMe | 89.97 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Vanilla | 89.97 | Not recorded | 69c21ad30636e5bf4afc4d18 | | A-Mem | 89.97 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Naïve RAG | 89.06 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Vanilla | 87.87 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Mem0 | 86.63 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Mem0g | 86.32 | Not recorded | 69c21ad30636e5bf4afc4d18 | | FLEX | 83.59 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Mem0g | 83.28 | Not recorded | 69c21ad30636e5bf4afc4d18 | | GraphRAG | 81.16 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Mem0 | 73.44 | Not recorded | 69c21ad30636e5bf4afc4d18 | ### GSEM Accuracy: 94.22. Result ID: 69c2c4e947f34ce924ac81e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### A-Mem Accuracy: 93.62. Result ID: 69c2c4e947f34ce924ac81de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### FLEX Accuracy: 93.31. Result ID: 69c2c4e947f34ce924ac81e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### Naïve RAG Accuracy: 92.4. Result ID: 69c2c4e947f34ce924ac81da. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### ReMe Accuracy: 91.49. Result ID: 69c2c4e947f34ce924ac81e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### GSEM Accuracy: 91.49. Result ID: 69c2c4e947f34ce924ac81ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### GraphRAG Accuracy: 90.27. Result ID: 69c2c4e947f34ce924ac81db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### ReMe Accuracy: 89.97. Result ID: 69c2c4e947f34ce924ac81df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 89.97. Result ID: 69c2c4e947f34ce924ac81e2. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### A-Mem Accuracy: 89.97. Result ID: 69c2c4e947f34ce924ac81e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### Naïve RAG Accuracy: 89.06. Result ID: 69c2c4e947f34ce924ac81e3. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 87.87. Result ID: 69c2c4e947f34ce924ac81d9. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### Mem0 Accuracy: 86.63. Result ID: 69c2c4e947f34ce924ac81dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### Mem0g Accuracy: 86.32. Result ID: 69c2c4e947f34ce924ac81e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### FLEX Accuracy: 83.59. Result ID: 69c2c4e947f34ce924ac81e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### Mem0g Accuracy: 83.28. Result ID: 69c2c4e947f34ce924ac81dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### GraphRAG Accuracy: 81.16. Result ID: 69c2c4e947f34ce924ac81e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### Mem0 Accuracy: 73.44. Result ID: 69c2c4e947f34ce924ac81e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.