Medical Question Answering on MedXpertQA
22.2AccuracyMA-RAG-ext
Evaluation Results
| Method | Links | |
|---|---|---|
| MA-RAG-extBackbone=Qwen3-8B, Ranking Agent=extrinsic verification2026.02 | 22.2 | |
| MA-RAG-intBackbone=Qwen3-8B, Ranking Agent=intrinsic uncertainty2026.02 | 21.2 | |
| IDCBackbone=Llama-3.1-8B, Method Type=Iterative Distractor Curation2026.03 | 19.31 | |
| CoTBackbone=Qwen3-8B2026.02 | 18 | |
| TC-RAGBackbone=Qwen3-8B2026.02 | 18 | |
| FLAREBackbone=Qwen3-8B2026.02 | 17.7 | |
| SR-RAGBackbone=Qwen3-8B2026.02 | 17.3 | |
| FL-RAGBackbone=Qwen3-8B2026.02 | 17 | |
| Citrus-VSize=8B2026.03 | 16.9 | |
| FS-RAGBackbone=Qwen3-8B2026.02 | 16.5 | |
| LingshuSize=7B2026.03 | 16.5 | |
| MEDIC-ADSize=7B2026.03 | 16.5 | |
| FilterBackbone=Llama-3.1-8B, Method Type=Filtering non-convertible questions2026.03 | 16.45 | |
| Multi-RefineBackbone=Qwen3-8B2026.02 | 16.3 | |
| Orig.Backbone=Llama-3.1-8B, Method Type=Standard RLVR on original MCQs2026.03 | 16.29 | |
| Qwen3-8BBackbone=Qwen3-8B2026.02 | 16.1 | |
| SCBackbone=Qwen3-8B2026.02 | 15.7 | |
| RewriteBackbone=Llama-3.1-8B, Method Type=Model-based conversion2026.03 | 15.67 | |
| HuatuoGPT-o1-8BBackbone=HuatuoGPT-o1-8B2026.02 | 15.5 | |
| DirectBackbone=Llama-3.1-8B, Method Type=Direct conversion to short-answer2026.03 | 15.47 | |
| BaseBackbone=Llama-3.1-8B, Method Type=Base instruct model2026.03 | 14.29 | |
| UltraMedical-3.1-8BBackbone=UltraMedical-3.1-8B2026.02 | 13.1 | |
| Llama-3.1-8BBackbone=Llama-3.1-8B2026.02 | 12.4 | |
| IDCBackbone=Qwen2-7B, Method Type=Iterative Distractor Curation2026.03 | 11.88 | |
| Orig.Backbone=Qwen2-7B, Method Type=Standard RLVR on original MCQs2026.03 | 10.98 | |
| LingshuSize=7B, Evaluation Protocol=full finetuning2026.03 | 10.9 | |
| FilterBackbone=Qwen2-7B, Method Type=Filtering non-convertible questions2026.03 | 10.86 | |
| DirectBackbone=Qwen2-7B, Method Type=Direct conversion to short-answer2026.03 | 10.29 | |
| BaseBackbone=Qwen2-7B, Method Type=Base instruct model2026.03 | 10.24 | |
| RewriteBackbone=Qwen2-7B, Method Type=Model-based conversion2026.03 | 10.24 | |
| LLaVA-MedSize=7B2026.03 | 9.9 |