# Medical Question Answering on Medicine Source: [Medical Question Answering on Medicine]() Collection index: [llms.txt]() Data updated: 2026-05-19T08:31:37.163Z Evaluation of model performance on the Medicine dataset for the Medical Question Answering task, reporting Accuracy scores. 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 Question Answering | | Dataset (including any stated split) | Medicine | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 | | --- | --- | --- | --- | | NeuroMAS-3 | 48 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | GPTSwarm | 43.5 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | NeuroMAS-7 | 43.5 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | Single-LLM RL | 43 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | NeuroMAS-5 | 41.5 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | MoA | 40.5 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | AgentNet | 39 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | MALT | 38 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | Self-Refine | 37.5 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | GoA | 34 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | CoLLM-CC | 33 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | Self-Check | 32.5 | Not recorded | 6a0beeafdbc836b87d82c4c7 | | Direct prompting | 24 | Not recorded | 6a0beeafdbc836b87d82c4c7 | ### NeuroMAS-3 Accuracy: 48. Result ID: 6a0c1ef6fbc373592c022a9a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"6.9M","LLM Calls":"3"}. This record does not assert independent reproduction. ### GPTSwarm Accuracy: 43.5. Result ID: 6a0c1ef6fbc373592c022a95. [Reporting paper]() Recorded evaluation configuration: {"Trainable Params":"0","LLM Calls":"11"}. This record does not assert independent reproduction. ### NeuroMAS-7 Accuracy: 43.5. Result ID: 6a0c1ef6fbc373592c022a9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"16.1M","LLM Calls":"7"}. This record does not assert independent reproduction. ### Single-LLM RL Accuracy: 43. Result ID: 6a0c1ef6fbc373592c022a99. [Reporting paper]() Recorded evaluation configuration: {"Trainable Params":"6.9M","LLM Calls":"1"}. This record does not assert independent reproduction. ### NeuroMAS-5 Accuracy: 41.5. Result ID: 6a0c1ef6fbc373592c022a9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"11.5M","LLM Calls":"5"}. This record does not assert independent reproduction. ### MoA Accuracy: 40.5. Result ID: 6a0c1ef6fbc373592c022a93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"0","LLM Calls":"5"}. This record does not assert independent reproduction. ### AgentNet Accuracy: 39. Result ID: 6a0c1ef6fbc373592c022a96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"0","LLM Calls":"11"}. This record does not assert independent reproduction. ### MALT Accuracy: 38. Result ID: 6a0c1ef6fbc373592c022a97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"6.9M","LLM Calls":"3"}. This record does not assert independent reproduction. ### Self-Refine Accuracy: 37.5. Result ID: 6a0c1ef6fbc373592c022a91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"0","LLM Calls":"2"}. This record does not assert independent reproduction. ### GoA Accuracy: 34. Result ID: 6a0c1ef6fbc373592c022a94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"0","LLM Calls":"3"}. This record does not assert independent reproduction. ### CoLLM-CC Accuracy: 33. Result ID: 6a0c1ef6fbc373592c022a98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"4.6M","LLM Calls":"2"}. This record does not assert independent reproduction. ### Self-Check Accuracy: 32.5. Result ID: 6a0c1ef6fbc373592c022a92. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Params":"0","LLM Calls":"2"}. This record does not assert independent reproduction. ### Direct prompting Accuracy: 24. Result ID: 6a0c1ef6fbc373592c022a90. [Reporting paper]() Recorded evaluation configuration: {"Trainable Params":"0","LLM Calls":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.