List your company

Commonsense Reasoning on OBQA (Normalized Accuracy)

34.6Normalized AccuracyMHF (H4B16K)
24.61627.20829.832.392Jun 26, 2026

Evaluation results

MethodLinks
MHF (H4B16K)Model Scale=3B, Embedding Parameters (Emb)=138M, Decoder Parameters (Dec)=2.8B, Evaluation Protocol=Zero-shot2026.0634.6
MHF (H3B10K)Model Scale=1B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=0.9B, Evaluation Protocol=Zero-shot2026.0634
StandardModel Scale=3B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=2.8B, Evaluation Protocol=Zero-shot2026.0631.8
StandardModel Scale=1B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=0.9B, Evaluation Protocol=Zero-shot2026.0631.6
Standard+2LModel Scale=1B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=1.0B, Evaluation Protocol=Zero-shot2026.0631.2
MHF (H4B16K)Model Scale=1B, Embedding Parameters (Emb)=138M, Decoder Parameters (Dec)=0.9B, Evaluation Protocol=Zero-shot2026.0629.8
MHF (H4B16K)Model Scale=100M, Embedding Parameters (Emb)=52M, Decoder Parameters (Dec)=87M, Evaluation Protocol=Zero-shot2026.0627.6
StandardModel Scale=100M, Embedding Parameters (Emb)=25M, Decoder Parameters (Dec)=87M, Evaluation Protocol=Zero-shot2026.0627
Standard+4LModel Scale=100M, Embedding Parameters (Emb)=25M, Decoder Parameters (Dec)=116M, Evaluation Protocol=Zero-shot2026.0627
MHF (H3B10K)Model Scale=100M, Embedding Parameters (Emb)=25M, Decoder Parameters (Dec)=87M, Evaluation Protocol=Zero-shot2026.0626.4
Rnd. GuessModel Scale=N/A, Embedding Parameters (Emb)=-, Decoder Parameters (Dec)=-, Evaluation Protocol=Random Guessing2026.0625