Biomedical Question Answering on BioACE automatic evaluation N=50 runs
94.96Precisionagent_faiss_deepseek
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| agent_faiss_deepseekTeam=dal2026.03 | 94.96 | 38.42 | 82.94 | 64.32 | |
| rrf_llama70b_no-valTeam=dal2026.03 | 94.68 | 37.86 | 89.99 | 67.26 | |
| hltbio-lg.fsrrfTeam=hltbio2026.03 | 93.22 | 40.27 | 72.95 | 68.04 | |
| hltbio-lg.fsrrfprfTeam=hltbio2026.03 | 92.52 | 37.82 | 63.77 | 69.67 | |
| pubmedbert_medcpt_gpt4oTeam=GEHC-HTIC2026.03 | 89.02 | 35.42 | 59.83 | 67.56 | |
| task_b_baselineTeam=Baseline2026.03 | 82.23 | 32.5 | 49.73 | 60 |