List your company

Code Generation on MBPP (Acc, F1, Avg. Tokens (K))

85.68AccuracySmolagent
78.81680.59882.3884.162Oct 30, 2025

Evaluation results

MethodLinks
Smolagent2025.1085.6885.68111.07
SUPERVISORAGENTmodule=SMAS, base_agent=Smolagent2025.1084.4384.43103.71
CoT SCshots=3-shot2025.1081.2681.261.29
Vanilla2025.1080.0980.090.27
MetaAgent2025.1079.8679.866.39
OWL2025.1079.0879.0854.8