List your company

Mathematical Reasoning on SVAMP (Reusability Score)

71.11Reusability ScoreLlama
19.380432.810246.2459.6698Feb 19, 2026

Evaluation results

MethodLinks
LlamaExecutor=Strong Comm.2026.0271.11
LlamaExecutor=Full Comm.2026.0265.43
LlamaExecutor=Weak Comm.2026.0259.75
PhiExecutor=Strong Comm.2026.0259.56
GemmaExecutor=Strong Comm.2026.0256.9
R1Executor=Strong Comm.2026.0245.76
PhiExecutor=Full Comm.2026.0243.69
GemmaExecutor=Full Comm.2026.0239.14
R1Executor=Full Comm.2026.0233.79
PhiExecutor=Weak Comm.2026.0227.82
R1Executor=Weak Comm.2026.0221.83
GemmaExecutor=Weak Comm.2026.0221.37