List your company

Mathematical Reasoning on SVAMP (Verifiability Score)

97.33Verifiability ScorePhi
61.626870.895980.16589.4341Feb 19, 2026

Evaluation results

MethodLinks
PhiExecutor=Strong Comm.2026.0297.33
R1Executor=Strong Comm.2026.0291.33
PhiExecutor=Full Comm.2026.0289.13
GemmaExecutor=Strong Comm.2026.0286.93
LlamaExecutor=Strong Comm.2026.0280.93
PhiExecutor=Weak Comm.2026.0280.93
R1Executor=Full Comm.2026.0280.33
GemmaExecutor=Full Comm.2026.0278.57
LlamaExecutor=Full Comm.2026.0271.97
GemmaExecutor=Weak Comm.2026.0270.2
R1Executor=Weak Comm.2026.0269.33
LlamaExecutor=Weak Comm.2026.0263