Our new X account is live! Follow @wizwand_team for updates

Code Generation on HumanEval++

98.44Accuracy

AFlow

Updated 4d ago

Evaluation Results

Method	Links
AFlow 2026.02		98.44
MASRouter 2026.02		98.44
MASRouter 2026.02		96.88
HieraMAS 2026.02		96.88
AFlow 2026.02		95.31
GDesigner 2026.02		93.75
HieraMAS 2026.02		93.75
Full-Graph 2026.02		92.19
Random-Graph 2026.02		92.19
Self-Consistency+CoT 2026.02		90.62
GDesigner 2026.02		90.62
Base 2026.02		89.06
Self-Consistency 2026.02		89.06
Full-Graph 2026.02		89.06
CoT 2026.02		87.5
Self-Consistency 2026.02		87.5
LLM-Debate 2026.02		87.5
LLM-Debate 2026.02		87.5
CoT 2026.02		85.94
Self-Consistency+CoT 2026.02		85.94
Random-Graph 2026.02		85.94
Base 2026.02		84.14