List your company

Medical Question Answering on MedQA, MedMCQA, and PubMedQA Aggregate

60.3MedQA AccuracyMed42-v2-Evontree (implicit)
42.72447.28751.8556.413Oct 30, 2025

Evaluation results

MethodLinks
Med42-v2-Evontree (implicit)Setting=SFT (on evaluation)2025.1060.362.478.967.2
OntoTune_sftSetting=SFT (on evaluation)2025.1058.460.478.665.8
OntoTune_dpoSetting=SFT (on evaluation)2025.1058.360.779.466.1
OntoTune_sft+dpoSetting=SFT (on evaluation)2025.1058.260.578.965.9
Med42-v2Setting=SFT (on evaluation)2025.1057.858.174.663.5
Med42-v2-Evontree (mix)Setting=SFT (on evaluation)2025.1057.257.774.963.3
Med42-v2-Evontree (explicit)Setting=SFT (on evaluation)2025.1057.158.671.162.3
LLaMA3 8BSetting=SFT (on evaluation)2025.1056.453.977.262.5
TaxoLLaMASetting=SFT (on evaluation)2025.1055.957.577.663.7
OntoTune_dpoSetting=zero-shot2025.1053.357.265.558.7
LLaMA3 8B-Evontree (implicit)Setting=zero-shot2025.1052.754.472.960
OntoTune_sft+dpoSetting=zero-shot2025.1051.956.766.358.3
LLaMA3 8BSetting=zero-shot2025.1051.751.770.357.9
OntoTune_sftSetting=zero-shot2025.1051.556.77260.1
AloeSetting=SFT (on evaluation)2025.1051.156.875.461.1
LLaMA3 8B-Evontree (mix)Setting=zero-shot2025.105157.474.761
TaxoLLaMASetting=zero-shot2025.1050.546.173.456.7
LLaMA3 8B-Evontree (explicit)Setting=zero-shot2025.1043.448.676.456.1