List your company

Multi-task agent evaluation on Skill-MAS Evaluation Suite Aggregate

41.05Average Performance (%)Skill-MAS-optimized
13.978821.006928.03535.0631Jun 17, 2026

Evaluation results

MethodLinks
Skill-MAS-optimizedMeta-agent=DeepSeek-V4-Flash2026.0641.052.12
Skill-MAS-optimizedMeta-agent=Qwen3.5-Plus2026.0638.412.43
AFlowMeta-agent=DeepSeek-V4-Flash2026.0635.71.45
AOrchestraMeta-agent=DeepSeek-V4-Flash2026.0634.362.69
EvoAgentMeta-agent=DeepSeek-V4-Flash2026.0634.33.33
Skill-MAS-initMeta-agent=DeepSeek-V4-Flash2026.0633.721.14
Skill-MAS-initMeta-agent=Qwen3.5-Plus2026.0632.611.83
AFlowMeta-agent=Qwen3.5-Plus2026.0632.231.56
EvoAgentMeta-agent=Qwen3.5-Plus2026.0631.17.91
MAS-OrchestraMeta-agent=DeepSeek-V4-Flash2026.0631.051.98
Skill-MAS-optimizedMeta-agent=Gemini-3.1-Flash2026.0629.492.82
AOrchestraMeta-agent=Qwen3.5-Plus2026.0629.021.91
Skill-MAS-optimizedMeta-agent=GPT-5.4-Nano2026.0627.555.22
MAS-OrchestraMeta-agent=Qwen3.5-Plus2026.0626.921.35
EvoAgentMeta-agent=GPT-5.4-Nano2026.0624.836.26
MAS2Meta-agent=Qwen3.5-Plus2026.0622.894.04
Skill-MAS-initMeta-agent=Gemini-3.1-Flash2026.0621.682.63
AFlowMeta-agent=Gemini-3.1-Flash2026.0621.290.44
AOrchestraMeta-agent=GPT-5.4-Nano2026.0620.252.45
MAS2Meta-agent=DeepSeek-V4-Flash2026.0620.060.63
Skill-MAS-initMeta-agent=GPT-5.4-Nano2026.0619.644.24
EvoAgentMeta-agent=Gemini-3.1-Flash2026.0619.128.2
AFlowMeta-agent=GPT-5.4-Nano2026.0619.110.69
MAS-OrchestraMeta-agent=Gemini-3.1-Flash2026.0619.022.48
MAS-OrchestraMeta-agent=GPT-5.4-Nano2026.0618.991.84
AOrchestraMeta-agent=Gemini-3.1-Flash2026.0618.952.31
MAS2Meta-agent=GPT-5.4-Nano2026.0616.681.27
MAS2Meta-agent=Gemini-3.1-Flash2026.0615.020.91