List your company

Question Answering on MedQA (HS, Acc)

42.75HSBeavertails
-1.221210.194421.6133.0256Mar 10, 2026

Evaluation results

MethodLinks
BeavertailsModel=Qwen2.5, Mixing ratio (r)=0.12026.0342.7562.5
BeavertailsModel=Mistral, Mixing ratio (r)=0.12026.0342.6557.76
NoneModel=Mistral, Mixing ratio (r)=0.12026.0341.0156.93
BeavertailsModel=Llama3, Mixing ratio (r)=0.12026.0331.0561.56
NoneModel=Qwen2.5, Mixing ratio (r)=0.12026.0315.9162.27
BeavertailsModel=OLMo2, Mixing ratio (r)=0.12026.0314.5649.33
AegisModel=Qwen2.5, Mixing ratio (r)=0.12026.0313.2561.9
GR-SAPModel=Mistral, Mixing ratio (r)=0.12026.0313.0552.71
AegisModel=Mistral, Mixing ratio (r)=0.12026.0312.5155.01
GR-SAPModel=Qwen2.5, Mixing ratio (r)=0.12026.0310.8962.45
NoneModel=Llama3, Mixing ratio (r)=0.12026.034.7861.06
AegisModel=Llama3, Mixing ratio (r)=0.12026.034.561.51
AegisModel=OLMo2, Mixing ratio (r)=0.12026.032.0249.8
NoneModel=OLMo2, Mixing ratio (r)=0.12026.030.7449.49
GR-SAPModel=Llama3, Mixing ratio (r)=0.12026.030.761.32
OriginalModel=OLMo2, Mixing ratio (r)=0.12026.030.5450.07
GR-SAPModel=OLMo2, Mixing ratio (r)=0.12026.030.4749.04