List your company

Mathematical Reasoning on Humanity's Last Exam Math (test)

29.76AccuracySkill-MAS-optimized
1.23288.638916.04523.4511Jun 17, 2026

Evaluation results

MethodLinks
Skill-MAS-optimizedMeta-agent=Qwen3.5-Plus2026.0629.76
EvoAgentMeta-agent=Qwen3.5-Plus2026.0627.38
Skill-MAS-optimizedMeta-agent=DeepSeek-V4-Flash2026.0626.79
AFlowMeta-agent=Qwen3.5-Plus2026.0625
Skill-MAS-initMeta-agent=Qwen3.5-Plus2026.0624.4
Skill-MAS-optimizedMeta-agent=Gemini-3.1-Flash2026.0621.43
MAS-OrchestraMeta-agent=Qwen3.5-Plus2026.0621.43
AFlowMeta-agent=DeepSeek-V4-Flash2026.0621.43
Skill-MAS-initMeta-agent=DeepSeek-V4-Flash2026.0620.83
MAS-OrchestraMeta-agent=DeepSeek-V4-Flash2026.0620.24
AOrchestraMeta-agent=DeepSeek-V4-Flash2026.0619.64
Skill-MAS-optimizedMeta-agent=GPT-5.4-Nano2026.0618.45
MAS-OrchestraMeta-agent=Gemini-3.1-Flash2026.0617.26
MAS2Meta-agent=Qwen3.5-Plus2026.0616.56
Skill-MAS-initMeta-agent=Gemini-3.1-Flash2026.0614.88
MAS-OrchestraMeta-agent=GPT-5.4-Nano2026.0614.88
EvoAgentMeta-agent=GPT-5.4-Nano2026.0614.29
Skill-MAS-initMeta-agent=GPT-5.4-Nano2026.0612.5
AOrchestraMeta-agent=Qwen3.5-Plus2026.0612.5
AFlowMeta-agent=GPT-5.4-Nano2026.0611.31
MAS2Meta-agent=GPT-5.4-Nano2026.0610.42
EvoAgentMeta-agent=DeepSeek-V4-Flash2026.069.52
EvoAgentMeta-agent=Gemini-3.1-Flash2026.068.93
AOrchestraMeta-agent=GPT-5.4-Nano2026.068.93
AOrchestraMeta-agent=Gemini-3.1-Flash2026.067.14
MAS2Meta-agent=DeepSeek-V4-Flash2026.066.67
AFlowMeta-agent=Gemini-3.1-Flash2026.065.95
MAS2Meta-agent=Gemini-3.1-Flash2026.062.33