List your company

Code Generation on HumanEval (Accuracy and Average Cost)

75.76AccuracyMACA (Ours)
54.564860.067465.5771.0726May 25, 2026

Evaluation results

MethodLinks
MACA (Ours)Model=Llama-3.1-8B, Structure Adaptation=✓, Orchestration Adaptation=✓2026.0575.762,100.1
DyLANModel=Llama-3.1-8B, Structure Adaptation=✗, Orchestration Adaptation=✗2026.0572.7315,256.7
PuppeteerModel=Llama-3.1-8B, Structure Adaptation=✗, Orchestration Adaptation=✓2026.0571.492,798.3
MacNetModel=Llama-3.1-8B, Structure Adaptation=✗, Orchestration Adaptation=✗2026.0568.188,782.6
AgentVerseModel=Llama-3.1-8B, Structure Adaptation=✗, Orchestration Adaptation=✗2026.0566.186,826.9
MaASModel=Llama-3.1-8B, Structure Adaptation=✓, Orchestration Adaptation=✗2026.0565.154,796.9
AgentPruneModel=Llama-3.1-8B, Structure Adaptation=✓, Orchestration Adaptation=✗2026.0562.52,357
Self-RefineModel=Llama-3.1-8B, Structure Adaptation=✗, Orchestration Adaptation=✗2026.0562.121,609.8
VanillaModel=Llama-3.1-8B, Structure Adaptation=✗, Orchestration Adaptation=✗2026.0560.61256.6
ComplexCoTModel=Llama-3.1-8B, Structure Adaptation=✗, Orchestration Adaptation=✗2026.0557.581,154.4
CoTModel=Llama-3.1-8B, Structure Adaptation=✗, Orchestration Adaptation=✗2026.0556.44297.9
SC (CoT×5)Model=Llama-3.1-8B, Structure Adaptation=✗, Orchestration Adaptation=✗2026.0555.382,389.6