List your company
ResearchFormerly WizWand

Open-ended Generation on TruthfulQA

70.13BLEURT ScoreFineSteer
50.338855.476960.61565.7531Apr 16, 2026
Updated 6mo ago

Evaluation results

MethodLinks
FineSteerBase Model=Gemma-2-9B-IT2026.0470.1370.9
TruthFlowBase Model=Gemma-2-9B-IT2026.0468.7466.01
FineSteerBase Model=Llama-3-8B-Instruct2026.0466.562.35
FineSteerBase Model=Llama-3-8B-Instruct2026.0466.562.35
FineSteerBase Model=Llama-3.2-3B-Instruct2026.0465.3154.79
AlphaSteerBase Model=Gemma-2-9B-IT2026.0464.5361.86
BiPOBase Model=Gemma-2-9B-IT2026.0464.1562.59
ITIBase Model=Gemma-2-9B-IT2026.0463.7961.37
FineSteerBase Model=Qwen2.5-7B-Instruct2026.0463.5754.28
FineSteerBase Model=Qwen2.5-7B-Instruct2026.0463.5754.28
CASTBase Model=Gemma-2-9B-IT2026.0462.7760.23
TruthFlowBase Model=Llama-3.2-3B-Instruct2026.0462.7350.61
Gemma-2-9B-IT2026.0462.3458.92
TruthFlowBase Model=Qwen2.5-7B-Instruct2026.0462.149.88
TruthFlowBase Model=Qwen2.5-7B-Instruct2026.0462.149.88
TruthFlowBase Model=Llama-3-8B-Instruct2026.0461.6654.77
TruthFlowBase Model=Llama-3-8B-Instruct2026.0461.6654.77
DoLaBase Model=Gemma-2-9B-IT2026.0461.5359.9
ITIBase Model=Qwen2.5-7B-Instruct2026.0460.1747.92
ITIBase Model=Qwen2.5-7B-Instruct2026.0460.1747.92
CASTBase Model=Qwen2.5-7B-Instruct2026.0459.6648.17
CASTBase Model=Qwen2.5-7B-Instruct2026.0459.6648.17
Qwen2.5-7B-InstructBase Model=Qwen2.5-7B-Instruct2026.0459.4148.41
Qwen2.5-7B-Instruct2026.0459.4148.41
AlphaSteerBase Model=Qwen2.5-7B-Instruct2026.0458.6848.66
AlphaSteerBase Model=Qwen2.5-7B-Instruct2026.0458.6848.66
BiPOBase Model=Qwen2.5-7B-Instruct2026.0458.4447.92
BiPOBase Model=Qwen2.5-7B-Instruct2026.0458.4447.92
DoLaBase Model=Qwen2.5-7B-Instruct2026.0457.2147.43
AlphaSteerBase Model=Llama-3.2-3B-Instruct2026.0457.2150.37
DoLaBase Model=Qwen2.5-7B-Instruct2026.0457.2147.43
CASTBase Model=Llama-3.2-3B-Instruct2026.0456.7247.19
BiPOBase Model=Llama-3.2-3B-Instruct2026.0455.7447.95
CASTBase Model=Llama-3-8B-Instruct2026.0454.9250.32
CASTBase Model=Llama-3-8B-Instruct2026.0454.9250.32
DoLaBase Model=Llama-3.2-3B-Instruct2026.0454.2842.05
ITIBase Model=Llama-3.2-3B-Instruct2026.0453.6645.97
AlphaSteerBase Model=Llama-3-8B-Instruct2026.0453.4251.83
AlphaSteerBase Model=Llama-3-8B-Instruct2026.0453.4251.83
Llama-3.2-3B-Instruct2026.0452.0941.08
BiPOBase Model=Llama-3-8B-Instruct2026.0451.9848.9
BiPOBase Model=Llama-3-8B-Instruct2026.0451.9848.9
DoLaBase Model=Llama-3-8B-Instruct2026.0451.3447.43
DoLaBase Model=Llama-3-8B-Instruct2026.0451.3447.43
ITIBase Model=Llama-3-8B-Instruct2026.0451.2350.37
ITIBase Model=Llama-3-8B-Instruct2026.0451.2350.37
Llama-3-8B-InstructBase Model=Llama-3-8B-Instruct2026.0451.145.48
Llama-3-8B-Instruct2026.0451.145.48