List your company

Question Answering on TruthfulQA (vbal Metric)

0.685vbalBase
-0.099160.104420.3080.51158Apr 6, 2026

Evaluation results

MethodLinks
BaseModel=Tulu3.1-8B2026.040.685
BaseModel=OLMo2-7B2026.040.67
BaseModel=Llama3.1-8B2026.040.636
Oracle-rephraseModel=Llama3.1-8B2026.040.069
Oracle-rephraseModel=Tulu3.1-8B2026.040.038
SIMPL.Model=Llama3.1-8B2026.040.026
Oracle-rephraseModel=OLMo2-7B2026.040.026
STRUCT.Model=Llama3.1-8B2026.040.022
STRUCT.Model=Tulu3.1-8B2026.040.013
PROF.Model=Llama3.1-8B2026.040.009
Reflect-and-rephraseModel=Llama3.1-8B2026.040.007
SIMPL.Model=Tulu3.1-8B2026.040.002
PROF.Model=Tulu3.1-8B2026.04-0.004
PROF.Model=OLMo2-7B2026.04-0.011
SIMPL.Model=OLMo2-7B2026.04-0.011
STRUCT.Model=OLMo2-7B2026.04-0.014
Reflect-and-rephraseModel=OLMo2-7B2026.04-0.027
Reflect-and-rephraseModel=Tulu3.1-8B2026.04-0.069