List your company

Mathematical Reasoning on GSM8K (Reusability Score)

94.68Reusability ScorePhi
46.746459.190771.63584.0793Feb 19, 2026

Evaluation results

MethodLinks
PhiExecutor=Strong Comm.2026.0294.68
LlamaExecutor=Strong Comm.2026.0287.82
R1Executor=Strong Comm.2026.0284.54
PhiExecutor=Full Comm.2026.0283.53
GemmaExecutor=Strong Comm.2026.0280.75
LlamaExecutor=Full Comm.2026.0273.46
PhiExecutor=Weak Comm.2026.0272.37
R1Executor=Full Comm.2026.0266.56
GemmaExecutor=Full Comm.2026.0266.04
LlamaExecutor=Weak Comm.2026.0259.1
GemmaExecutor=Weak Comm.2026.0251.33
R1Executor=Weak Comm.2026.0248.59