List your company

Mathematical Reasoning on GSM8K (Verifiability Score)

97.82Verifiability ScorePhi
58.175268.467678.7689.0524Feb 19, 2026

Evaluation results

MethodLinks
PhiExecutor=Strong Comm.2026.0297.82
R1Executor=Strong Comm.2026.0293.37
GemmaExecutor=Strong Comm.2026.0291.48
PhiExecutor=Full Comm.2026.0288.36
LlamaExecutor=Strong Comm.2026.0282.97
R1Executor=Full Comm.2026.0280.33
GemmaExecutor=Full Comm.2026.0279.46
PhiExecutor=Weak Comm.2026.0278.91
LlamaExecutor=Full Comm.2026.0271.33
GemmaExecutor=Weak Comm.2026.0267.45
R1Executor=Weak Comm.2026.0267.29
LlamaExecutor=Weak Comm.2026.0259.7