List your company

Commonsense Question Answering on CommonsenseQA (out-of-domain)

70.7AccuracyS2L-PO-4B
63.62865.46467.369.136May 29, 2026

Evaluation results

MethodLinks
S2L-PO-4BBase Model=Qwen3-14B-Base2026.0570.7
S2L-PO-4BBase Model=Qwen3-8B-Base2026.0567.8
GRPOBase Model=Qwen3-14B-Base2026.0567.2
S2L-PO-1.7BBase Model=Qwen3-8B-Base2026.0564.2
GRPOBase Model=Qwen3-8B-Base2026.0563.9