List your company

Heterogeneous Knowledge and Reasoning on MMLU (Accuracy)

52.7Accuracy (Heterogeneous Knowledge & Reasoning)Transformer
51.24451.6225252.378Jun 4, 2026

Evaluation results

MethodLinks
TransformerModel Scale=4B2026.0652.7
YOCO (Dense)Model Scale=4B2026.0651.9
YOCO (CLSA)Model Scale=4B, Attention=Cross-Layer Sparse2026.0651.3