# Multimodal Clinical Reasoning on AgentClinic\_M offline (test) Source: [Multimodal Clinical Reasoning on AgentClinic\_M offline (test)]() Collection index: [llms.txt]() Data updated: 2026-06-09T10:54:24.575Z Evaluation of model performance on the Multimodal Clinical Reasoning task using the test split of the AgentClinic\_M offline dataset, 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 | Multimodal Clinical Reasoning | | Dataset (including any stated split) | AgentClinic\_M offline (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 38 of 38 | | 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 | | --- | --- | --- | --- | | SkeMex | 94.17 | Not recorded | 6a279e5e90966ade919bfa97 | | Memp | 90.83 | Not recorded | 6a279e5e90966ade919bfa97 | | Evolver | 90.83 | Not recorded | 6a279e5e90966ade919bfa97 | | DC | 90.83 | Not recorded | 6a279e5e90966ade919bfa97 | | Reflexion | 90 | Not recorded | 6a279e5e90966ade919bfa97 | | Voyager | 90 | Not recorded | 6a279e5e90966ade919bfa97 | | CFM | 90 | Not recorded | 6a279e5e90966ade919bfa97 | | SkeMex | 89.17 | Not recorded | 6a279e5e90966ade919bfa97 | | DILU | 89.17 | Not recorded | 6a279e5e90966ade919bfa97 | | ExPeL | 89.17 | Not recorded | 6a279e5e90966ade919bfa97 | | GM | 89.17 | Not recorded | 6a279e5e90966ade919bfa97 | | Agent KB | 89.17 | Not recorded | 6a279e5e90966ade919bfa97 | | MobileE | 89.17 | Not recorded | 6a279e5e90966ade919bfa97 | | GSEM | 89.17 | Not recorded | 6a279e5e90966ade919bfa97 | | GSEM | 88.33 | Not recorded | 6a279e5e90966ade919bfa97 | | SkillWeaver | 88.33 | Not recorded | 6a279e5e90966ade919bfa97 | | AWM | 88.33 | Not recorded | 6a279e5e90966ade919bfa97 | | CRITIC | 86.67 | Not recorded | 6a279e5e90966ade919bfa97 | | ReAct | 85 | Not recorded | 6a279e5e90966ade919bfa97 | | CoT | 84.17 | Not recorded | 6a279e5e90966ade919bfa97 | | Reflexion | 84.17 | Not recorded | 6a279e5e90966ade919bfa97 | | Memp | 84.17 | Not recorded | 6a279e5e90966ade919bfa97 | | SkillWeaver | 84.17 | Not recorded | 6a279e5e90966ade919bfa97 | | Agent KB | 84.17 | Not recorded | 6a279e5e90966ade919bfa97 | | CFM | 84.17 | Not recorded | 6a279e5e90966ade919bfa97 | | CoT | 83.33 | Not recorded | 6a279e5e90966ade919bfa97 | | ReAct | 83.33 | Not recorded | 6a279e5e90966ade919bfa97 | | GM | 83.33 | Not recorded | 6a279e5e90966ade919bfa97 | | DC | 83.33 | Not recorded | 6a279e5e90966ade919bfa97 | | MobileE | 83.33 | Not recorded | 6a279e5e90966ade919bfa97 | | ExPeL | 82.5 | Not recorded | 6a279e5e90966ade919bfa97 | | CoT | 80.83 | Not recorded | 6a279e5e90966ade919bfa97 | | CRITIC | 80 | Not recorded | 6a279e5e90966ade919bfa97 | | Evolver | 80 | Not recorded | 6a279e5e90966ade919bfa97 | | Voyager | 79.17 | Not recorded | 6a279e5e90966ade919bfa97 | | DILU | 79.17 | Not recorded | 6a279e5e90966ade919bfa97 | | AWM | 79.17 | Not recorded | 6a279e5e90966ade919bfa97 | | CoT | 73.33 | Not recorded | 6a279e5e90966ade919bfa97 | ### SkeMex Accuracy: 94.17. Result ID: 6a27ef25fbc373592c2586fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Memp Accuracy: 90.83. Result ID: 6a27ef25fbc373592c2586f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Evolver Accuracy: 90.83. Result ID: 6a27ef25fbc373592c2586f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### DC Accuracy: 90.83. Result ID: 6a27ef25fbc373592c2586f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Reflexion Accuracy: 90. Result ID: 6a27ef25fbc373592c2586ec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Voyager Accuracy: 90. Result ID: 6a27ef25fbc373592c2586ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### CFM Accuracy: 90. Result ID: 6a27ef25fbc373592c2586f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### SkeMex Accuracy: 89.17. Result ID: 6a27ef25fbc373592c2586ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### DILU Accuracy: 89.17. Result ID: 6a27ef25fbc373592c2586ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### ExPeL Accuracy: 89.17. Result ID: 6a27ef25fbc373592c2586f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### GM Accuracy: 89.17. Result ID: 6a27ef25fbc373592c2586f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Agent KB Accuracy: 89.17. Result ID: 6a27ef25fbc373592c2586f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### MobileE Accuracy: 89.17. Result ID: 6a27ef25fbc373592c2586f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### GSEM Accuracy: 89.17. Result ID: 6a27ef25fbc373592c2586fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### GSEM Accuracy: 88.33. Result ID: 6a27ef25fbc373592c2586e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### SkillWeaver Accuracy: 88.33. Result ID: 6a27ef25fbc373592c2586f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### AWM Accuracy: 88.33. Result ID: 6a27ef25fbc373592c2586f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### CRITIC Accuracy: 86.67. Result ID: 6a27ef25fbc373592c2586ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### ReAct Accuracy: 85. Result ID: 6a27ef25fbc373592c2586eb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### CoT Accuracy: 84.17. Result ID: 6a27ef25fbc373592c2586d6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Hulu-Med-32B","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Reflexion Accuracy: 84.17. Result ID: 6a27ef25fbc373592c2586db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Memp Accuracy: 84.17. Result ID: 6a27ef25fbc373592c2586e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### SkillWeaver Accuracy: 84.17. Result ID: 6a27ef25fbc373592c2586e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Agent KB Accuracy: 84.17. Result ID: 6a27ef25fbc373592c2586e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### CFM Accuracy: 84.17. Result ID: 6a27ef25fbc373592c2586e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### CoT Accuracy: 83.33. Result ID: 6a27ef25fbc373592c2586d8. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"MedGemma-27B","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### ReAct Accuracy: 83.33. Result ID: 6a27ef25fbc373592c2586da. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### GM Accuracy: 83.33. Result ID: 6a27ef25fbc373592c2586e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### DC Accuracy: 83.33. Result ID: 6a27ef25fbc373592c2586e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### MobileE Accuracy: 83.33. Result ID: 6a27ef25fbc373592c2586e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### ExPeL Accuracy: 82.5. Result ID: 6a27ef25fbc373592c2586df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### CoT Accuracy: 80.83. Result ID: 6a27ef25fbc373592c2586d9. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### CRITIC Accuracy: 80. Result ID: 6a27ef25fbc373592c2586dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Evolver Accuracy: 80. Result ID: 6a27ef25fbc373592c2586e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### Voyager Accuracy: 79.17. Result ID: 6a27ef25fbc373592c2586dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### DILU Accuracy: 79.17. Result ID: 6a27ef25fbc373592c2586de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### AWM Accuracy: 79.17. Result ID: 6a27ef25fbc373592c2586e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. ### CoT Accuracy: 73.33. Result ID: 6a27ef25fbc373592c2586d7. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Lingshu-32B","Evaluation Setting":"Offline"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.