# Medical Question Answering on MedicationQA full n=674 (test) Source: [Medical Question Answering on MedicationQA full n=674 (test)]() Collection index: [llms.txt]() Data updated: 2026-05-26T13:30:19.276Z Evaluation of model performance on the specific test split (n=674) of the MedicationQA dataset for Medical Question Answering, measured using F1 and R-L 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) | MedicationQA full n=674 (test) | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [ROUGE-L](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | MedBioLM | 22 | Not recorded | 6a15297adbd7150506f7e475 | | Qwen3-4B MedNLI-Cls | 19.1 | Not recorded | 6a15297adbd7150506f7e475 | | Qwen3-4B Likelihood-NLI | 18.5 | Not recorded | 6a15297adbd7150506f7e475 | | Qwen2.5-7B MedNLI-Cls | 17 | Not recorded | 6a15297adbd7150506f7e475 | | GPT-4o (FT) | 15.8 | Not recorded | 6a15297adbd7150506f7e475 | | Qwen2.5-7B Likelihood-NLI | 15 | Not recorded | 6a15297adbd7150506f7e475 | | Qwen2.5-7B GPT-NLI | 14.9 | Not recorded | 6a15297adbd7150506f7e475 | | Qwen2.5-7B Hybrid | 14 | Not recorded | 6a15297adbd7150506f7e475 | ### MedBioLM F1 Score: 22. Result ID: 6a15a056fbc373592c0eb183. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"FT + RAG"}. This record does not assert independent reproduction. ### Qwen3-4B MedNLI-Cls F1 Score: 19.1. Result ID: 6a15a056fbc373592c0eb181. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"4B + RL"}. This record does not assert independent reproduction. ### Qwen3-4B Likelihood-NLI F1 Score: 18.5. Result ID: 6a15a056fbc373592c0eb180. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"4B + RL"}. This record does not assert independent reproduction. ### Qwen2.5-7B MedNLI-Cls F1 Score: 17. Result ID: 6a15a056fbc373592c0eb17d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"7B + RL"}. This record does not assert independent reproduction. ### GPT-4o (FT) F1 Score: 15.8. Result ID: 6a15a056fbc373592c0eb182. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"FT"}. This record does not assert independent reproduction. ### Qwen2.5-7B Likelihood-NLI F1 Score: 15. Result ID: 6a15a056fbc373592c0eb17c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"7B + RL"}. This record does not assert independent reproduction. ### Qwen2.5-7B GPT-NLI F1 Score: 14.9. Result ID: 6a15a056fbc373592c0eb17f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"7B + RL"}. This record does not assert independent reproduction. ### Qwen2.5-7B Hybrid F1 Score: 14. Result ID: 6a15a056fbc373592c0eb17e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"7B + RL"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.