List your company

Commonsense Question Answering on Commonsense QA

50.97Reusability ScorePhi
28.256434.153240.0545.9468Feb 19, 2026

Evaluation results

MethodLinks
PhiExecutor=Strong Comm.2026.0250.97
PhiExecutor=Full Comm.2026.0243.52
LlamaExecutor=Strong Comm.2026.0239.12
LlamaExecutor=Full Comm.2026.0236.55
PhiExecutor=Weak Comm.2026.0236.07
GemmaExecutor=Strong Comm.2026.0234.92
R1Executor=Strong Comm.2026.0234.69
GemmaExecutor=Full Comm.2026.0234.29
LlamaExecutor=Weak Comm.2026.0233.97
GemmaExecutor=Weak Comm.2026.0233.67
R1Executor=Full Comm.2026.0231.91
R1Executor=Weak Comm.2026.0229.13