Close-ended QA on PubMedQA
85AccuracyFine-Tuned GPT-4o + MedBioRAG
Evaluation Results
| Method | Links | |
|---|---|---|
| Fine-Tuned GPT-4o + MedBioRAGBackbone=GPT-4o, Fine-tuned=true, RAG=MedBioRAG2025.12 | 85 | |
| Fine-Tuned GPT-4oBackbone=GPT-4o, Fine-tuned=true2025.12 | 80.7 | |
| GPT-4o-miniBackbone=GPT-4o-mini, Fine-tuned=false2025.12 | 77.55 | |
| GPT-4o-mini + MedBioRAGBackbone=GPT-4o-mini, Fine-tuned=false, RAG=MedBioRAG2025.12 | 76.32 | |
| GPT-4 + MedBioRAGBackbone=GPT-4, Fine-tuned=false, RAG=MedBioRAG2025.12 | 72.81 | |
| GPT-4o + MedBioRAGBackbone=GPT-4o, Fine-tuned=false, RAG=MedBioRAG2025.12 | 66.67 | |
| GPT-4Backbone=GPT-4, Fine-tuned=false2025.12 | 52.63 | |
| GPT-4oBackbone=GPT-4o, Fine-tuned=false2025.12 | 44.74 | |
| GPT-3.5 + MedBioRAGBackbone=GPT-3.5, Fine-tuned=false, RAG=MedBioRAG2025.12 | 38.6 | |
| GPT-3.5Backbone=GPT-3.5, Fine-tuned=false2025.12 | 19.3 |