# Medical Question Answering on EHRNoteQA Source: [Medical Question Answering on EHRNoteQA]() Collection index: [llms.txt]() Data updated: 2026-06-02T06:35:20.298Z Evaluation of model performance on the EHRNoteQA dataset for Medical Question Answering, utilizing statistical metrics like Calibrated Accuracy, Delta (Δ), and p-value. 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) | EHRNoteQA | | Metric | Calibrated Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Calibrated Accuracy](): Higher is better; unit: PERCENT. - [Delta (Δ)](): Higher is better; unit: SCALAR. - [p-value](): Lower is better; unit: SCALAR. ## Recorded results | Method | Calibrated Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-8B | 98 | Not recorded | 6a1e640cdbd7150506f85660 | | Qwen3-8B | 96.3 | Not recorded | 6a1e640cdbd7150506f85660 | | Llama-3.1-8B | 94.1 | Not recorded | 6a1e640cdbd7150506f85660 | | Qwen2.5-7B | 92.8 | Not recorded | 6a1e640cdbd7150506f85660 | | Llama-3.1-8B | 92.1 | Not recorded | 6a1e640cdbd7150506f85660 | | Qwen2.5-7B | 91.6 | Not recorded | 6a1e640cdbd7150506f85660 | | DeepSeek-R1-8B | 85.9 | Not recorded | 6a1e640cdbd7150506f85660 | | DeepSeek-R1-8B | 76.9 | Not recorded | 6a1e640cdbd7150506f85660 | | BioMistral-7B | 50.4 | Not recorded | 6a1e640cdbd7150506f85660 | | BioMistral-7B | 48.1 | Not recorded | 6a1e640cdbd7150506f85660 | ### Qwen3-8B Calibrated Accuracy: 98. Result ID: 6a1e78dcfbc373592c17e687. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Med-HEAL"}. This record does not assert independent reproduction. ### Qwen3-8B Calibrated Accuracy: 96.3. Result ID: 6a1e78dcfbc373592c17e686. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Llama-3.1-8B Calibrated Accuracy: 94.1. Result ID: 6a1e78dcfbc373592c17e683. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Med-HEAL"}. This record does not assert independent reproduction. ### Qwen2.5-7B Calibrated Accuracy: 92.8. Result ID: 6a1e78dcfbc373592c17e685. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Med-HEAL"}. This record does not assert independent reproduction. ### Llama-3.1-8B Calibrated Accuracy: 92.1. Result ID: 6a1e78dcfbc373592c17e682. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Qwen2.5-7B Calibrated Accuracy: 91.6. Result ID: 6a1e78dcfbc373592c17e684. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### DeepSeek-R1-8B Calibrated Accuracy: 85.9. Result ID: 6a1e78dcfbc373592c17e681. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Med-HEAL"}. This record does not assert independent reproduction. ### DeepSeek-R1-8B Calibrated Accuracy: 76.9. Result ID: 6a1e78dcfbc373592c17e680. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### BioMistral-7B Calibrated Accuracy: 50.4. Result ID: 6a1e78dcfbc373592c17e67f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Med-HEAL"}. This record does not assert independent reproduction. ### BioMistral-7B Calibrated Accuracy: 48.1. Result ID: 6a1e78dcfbc373592c17e67e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.