List your company

Factual Reasoning on TruthfulQA MCQ

39.33MCQ AccuracySTAR-1
-1.27169.269219.8130.3508Jul 29, 2025

Evaluation results

MethodLinks
STAR-1Base Model=R1-8B2025.0739.33
UnsafeChainBase Model=R1-8B, Data Subset=random2025.0738.89
UnsafeChainBase Model=R1-8B, Data Subset=selected2025.0738.74
R1Model Size=8B2025.0737.43
UnsafeChainBase Model=R1-1.5B, Data Subset=full2025.0721.93
UnsafeChainBase Model=R1-1.5B, Data Subset=selected2025.0721.64
UnsafeChainBase Model=R1-1.5B, Data Subset=random2025.0720.61
STAR-1Base Model=R1-1.5B2025.0719.88
R1Model Size=1.5B2025.0718.57
SafeChainBase Model=R1-1.5B2025.0712.28
UnsafeChainBase Model=R1-8B, Data Subset=full2025.079.8
SafeChainBase Model=R1-8B2025.078.92
STAR-1Base Model=R1-7B2025.076.48
UnsafeChainBase Model=R1-7B, Data Subset=random2025.075.55
UnsafeChainBase Model=R1-7B, Data Subset=selected2025.074.68
R1Model Size=7B2025.073.22
UnsafeChainBase Model=R1-7B, Data Subset=full2025.070.44
SafeChainBase Model=R1-7B2025.070.29