# Clinical Reasoning on MedR-Bench Treatment Source: [Clinical Reasoning on MedR-Bench Treatment]() Collection index: [llms.txt]() Data updated: 2026-03-24T17:08:17.122Z Evaluation of model performance on the Clinical Reasoning task using the MedR-Bench Treatment dataset, typically measured by 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 Treatment | | 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 | 94.59 | Not recorded | 69c21ad30636e5bf4afc4d18 | | A-Mem | 92.57 | Not recorded | 69c21ad30636e5bf4afc4d18 | | ReMe | 89.19 | Not recorded | 69c21ad30636e5bf4afc4d18 | | FLEX | 89.19 | Not recorded | 69c21ad30636e5bf4afc4d18 | | GraphRAG | 87.16 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Naïve RAG | 84.46 | Not recorded | 69c21ad30636e5bf4afc4d18 | | GSEM | 66.89 | Not recorded | 69c21ad30636e5bf4afc4d18 | | A-Mem | 65.54 | Not recorded | 69c21ad30636e5bf4afc4d18 | | ReMe | 64.86 | Not recorded | 69c21ad30636e5bf4afc4d18 | | FLEX | 63.51 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Vanilla | 60.14 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Vanilla | 57.43 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Mem0 | 57.43 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Mem0g | 56.08 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Naïve RAG | 51.35 | Not recorded | 69c21ad30636e5bf4afc4d18 | | GraphRAG | 47.3 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Mem0 | 43.92 | Not recorded | 69c21ad30636e5bf4afc4d18 | | Mem0g | 43.92 | Not recorded | 69c21ad30636e5bf4afc4d18 | ### GSEM Accuracy: 94.59. Result ID: 69c2c4e947f34ce924ac81f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### A-Mem Accuracy: 92.57. Result ID: 69c2c4e947f34ce924ac81f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### ReMe Accuracy: 89.19. Result ID: 69c2c4e947f34ce924ac81f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### FLEX Accuracy: 89.19. Result ID: 69c2c4e947f34ce924ac81f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### GraphRAG Accuracy: 87.16. Result ID: 69c2c4e947f34ce924ac81ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### Naïve RAG Accuracy: 84.46. Result ID: 69c2c4e947f34ce924ac81ec. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### GSEM Accuracy: 66.89. Result ID: 69c2c4e947f34ce924ac81fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### A-Mem Accuracy: 65.54. Result ID: 69c2c4e947f34ce924ac81f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### ReMe Accuracy: 64.86. Result ID: 69c2c4e947f34ce924ac81fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### FLEX Accuracy: 63.51. Result ID: 69c2c4e947f34ce924ac81fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 60.14. Result ID: 69c2c4e947f34ce924ac81f4. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 57.43. Result ID: 69c2c4e947f34ce924ac81eb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### Mem0 Accuracy: 57.43. Result ID: 69c2c4e947f34ce924ac81ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### Mem0g Accuracy: 56.08. Result ID: 69c2c4e947f34ce924ac81ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### Naïve RAG Accuracy: 51.35. Result ID: 69c2c4e947f34ce924ac81f5. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### GraphRAG Accuracy: 47.3. Result ID: 69c2c4e947f34ce924ac81f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### Mem0 Accuracy: 43.92. Result ID: 69c2c4e947f34ce924ac81f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.5-35B"}. This record does not assert independent reproduction. ### Mem0g Accuracy: 43.92. Result ID: 69c2c4e947f34ce924ac81f8. [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.