List your company

Validity Certification on HH-RLHF (test)

100FTV@k=1TPA
9597.5100102.5Feb 10, 2026

Evaluation results

MethodLinks
TPAModel=OLMo-1B2026.0210010099.182.5754.7820.7819.6719.3414.699.21
TPA+MSCModel=OLMo-1B2026.021001001001009926.1325.6124.9624.2322.85
TPAModel=Gemma2-2B2026.0210010098.565.6326.1920.4919.0918.4513.128.19
TPA+MSCModel=Gemma2-2B2026.0210010010099.895.525.5624.9324.2523.2321.52
TPAModel=Qwen1.5-4B2026.0210098.9995.5972.5738.6125.4323.8721.8414.728.56
TPA+MSCModel=Qwen1.5-4B2026.0210010010099.292.5926.6425.8524.9123.5721.16