# Top-5 Ranking on Clinical IBD Clinical Ground Truth Mode 2 (10-patient pilot) Source: [Top-5 Ranking on Clinical IBD Clinical Ground Truth Mode 2 (10-patient pilot)]() Collection index: [llms.txt]() Data updated: 2026-06-18T08:22:39.702Z Evaluation of model performance on the Top-5 Ranking task using the Clinical IBD Clinical Ground Truth Mode 2 (10-patient pilot) dataset, measured by Precision@5 (P@5). 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 | Top-5 Ranking | | Dataset (including any stated split) | Clinical IBD Clinical Ground Truth Mode 2 (10-patient pilot) | | Metric | Precision@5 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | 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 - [Precision@5](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision@5 | Result date | Report paper | | --- | --- | --- | --- | | wald\_mag (priority-weighted rule) | 55.2 | Not recorded | 6a337b89206542251d7c501c | | cmi (priority-weighted rule) | 55.2 | Not recorded | 6a337b89206542251d7c501c | | F-target (clustered) | 55.2 | Not recorded | 6a337b89206542251d7c501c | | wald\_mag (priority-weighted rule) | 52.8 | Not recorded | 6a337b89206542251d7c501c | | F-target (clustered) | 48.4 | Not recorded | 6a337b89206542251d7c501c | | F-target (clustered) | 47.6 | Not recorded | 6a337b89206542251d7c501c | | cmi (priority-weighted rule) | 47.2 | Not recorded | 6a337b89206542251d7c501c | | wald\_mag (priority-weighted rule) | 46.8 | Not recorded | 6a337b89206542251d7c501c | | wald\_mag (priority-weighted rule) | 45.6 | Not recorded | 6a337b89206542251d7c501c | | cmi (priority-weighted rule) | 45.2 | Not recorded | 6a337b89206542251d7c501c | | cmi (priority-weighted rule) | 42.4 | Not recorded | 6a337b89206542251d7c501c | | F-target (clustered) | 42 | Not recorded | 6a337b89206542251d7c501c | | cmi (priority-weighted rule) | 41.6 | Not recorded | 6a337b89206542251d7c501c | | F-target (clustered) | 41.6 | Not recorded | 6a337b89206542251d7c501c | | wald\_mag (priority-weighted rule) | 41.2 | Not recorded | 6a337b89206542251d7c501c | | MRF-LLM | 26.4 | Not recorded | 6a337b89206542251d7c501c | | MRF-LLM | 23.3 | Not recorded | 6a337b89206542251d7c501c | | MRF-LLM | 23.2 | Not recorded | 6a337b89206542251d7c501c | | RAG-LLM | 20.7 | Not recorded | 6a337b89206542251d7c501c | | MRF-LLM | 20.3 | Not recorded | 6a337b89206542251d7c501c | | RAG-LLM | 19.8 | Not recorded | 6a337b89206542251d7c501c | | RAG-LLM | 19.7 | Not recorded | 6a337b89206542251d7c501c | | RAG-LLM | 19.7 | Not recorded | 6a337b89206542251d7c501c | | MRF-LLM | 18.7 | Not recorded | 6a337b89206542251d7c501c | | RAG-LLM | 18.3 | Not recorded | 6a337b89206542251d7c501c | ### wald\_mag (priority-weighted rule) Precision@5: 55.2. Result ID: 6a33aac0fbc373592c30e7a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"wald\_mag","Allocation":"priority-weighted rule","Acquisition budget (t)":"216"}. This record does not assert independent reproduction. ### cmi (priority-weighted rule) Precision@5: 55.2. Result ID: 6a33aac0fbc373592c30e7ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"cmi","Allocation":"priority-weighted rule","Acquisition budget (t)":"216"}. This record does not assert independent reproduction. ### F-target (clustered) Precision@5: 55.2. Result ID: 6a33aac0fbc373592c30e7b2. [Reporting paper]() Recorded evaluation configuration: {"Gain":"F-target","Allocation":"clustered","Acquisition budget (t)":"216"}. This record does not assert independent reproduction. ### wald\_mag (priority-weighted rule) Precision@5: 52.8. Result ID: 6a33aac0fbc373592c30e7a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"wald\_mag","Allocation":"priority-weighted rule","Acquisition budget (t)":"150"}. This record does not assert independent reproduction. ### F-target (clustered) Precision@5: 48.4. Result ID: 6a33aac0fbc373592c30e7b0. [Reporting paper]() Recorded evaluation configuration: {"Gain":"F-target","Allocation":"clustered","Acquisition budget (t)":"100"}. This record does not assert independent reproduction. ### F-target (clustered) Precision@5: 47.6. Result ID: 6a33aac0fbc373592c30e7b1. [Reporting paper]() Recorded evaluation configuration: {"Gain":"F-target","Allocation":"clustered","Acquisition budget (t)":"150"}. This record does not assert independent reproduction. ### cmi (priority-weighted rule) Precision@5: 47.2. Result ID: 6a33aac0fbc373592c30e7ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"cmi","Allocation":"priority-weighted rule","Acquisition budget (t)":"150"}. This record does not assert independent reproduction. ### wald\_mag (priority-weighted rule) Precision@5: 46.8. Result ID: 6a33aac0fbc373592c30e7a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"wald\_mag","Allocation":"priority-weighted rule","Acquisition budget (t)":"100"}. This record does not assert independent reproduction. ### wald\_mag (priority-weighted rule) Precision@5: 45.6. Result ID: 6a33aac0fbc373592c30e7a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"wald\_mag","Allocation":"priority-weighted rule","Acquisition budget (t)":"50"}. This record does not assert independent reproduction. ### cmi (priority-weighted rule) Precision@5: 45.2. Result ID: 6a33aac0fbc373592c30e7ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"cmi","Allocation":"priority-weighted rule","Acquisition budget (t)":"100"}. This record does not assert independent reproduction. ### cmi (priority-weighted rule) Precision@5: 42.4. Result ID: 6a33aac0fbc373592c30e7aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"cmi","Allocation":"priority-weighted rule","Acquisition budget (t)":"50"}. This record does not assert independent reproduction. ### F-target (clustered) Precision@5: 42. Result ID: 6a33aac0fbc373592c30e7af. [Reporting paper]() Recorded evaluation configuration: {"Gain":"F-target","Allocation":"clustered","Acquisition budget (t)":"50"}. This record does not assert independent reproduction. ### cmi (priority-weighted rule) Precision@5: 41.6. Result ID: 6a33aac0fbc373592c30e7a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"cmi","Allocation":"priority-weighted rule","Acquisition budget (t)":"10"}. This record does not assert independent reproduction. ### F-target (clustered) Precision@5: 41.6. Result ID: 6a33aac0fbc373592c30e7ae. [Reporting paper]() Recorded evaluation configuration: {"Gain":"F-target","Allocation":"clustered","Acquisition budget (t)":"10"}. This record does not assert independent reproduction. ### wald\_mag (priority-weighted rule) Precision@5: 41.2. Result ID: 6a33aac0fbc373592c30e7a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gain":"wald\_mag","Allocation":"priority-weighted rule","Acquisition budget (t)":"10"}. This record does not assert independent reproduction. ### MRF-LLM Precision@5: 26.4. Result ID: 6a33aac0fbc373592c30e7b7. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"216"}. This record does not assert independent reproduction. ### MRF-LLM Precision@5: 23.3. Result ID: 6a33aac0fbc373592c30e7b5. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"100"}. This record does not assert independent reproduction. ### MRF-LLM Precision@5: 23.2. Result ID: 6a33aac0fbc373592c30e7b6. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"150"}. This record does not assert independent reproduction. ### RAG-LLM Precision@5: 20.7. Result ID: 6a33aac0fbc373592c30e7b9. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"50"}. This record does not assert independent reproduction. ### MRF-LLM Precision@5: 20.3. Result ID: 6a33aac0fbc373592c30e7b4. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"50"}. This record does not assert independent reproduction. ### RAG-LLM Precision@5: 19.8. Result ID: 6a33aac0fbc373592c30e7b8. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"10"}. This record does not assert independent reproduction. ### RAG-LLM Precision@5: 19.7. Result ID: 6a33aac0fbc373592c30e7ba. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"100"}. This record does not assert independent reproduction. ### RAG-LLM Precision@5: 19.7. Result ID: 6a33aac0fbc373592c30e7bc. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"216"}. This record does not assert independent reproduction. ### MRF-LLM Precision@5: 18.7. Result ID: 6a33aac0fbc373592c30e7b3. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"10"}. This record does not assert independent reproduction. ### RAG-LLM Precision@5: 18.3. Result ID: 6a33aac0fbc373592c30e7bb. [Reporting paper]() Recorded evaluation configuration: {"Acquisition budget (t)":"150"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.