List your company

Web-based research on DeepResearchBench (test)

52.91AccuracyEvoAgent
34.60639.35844.1148.862Jun 17, 2026

Evaluation results

MethodLinks
EvoAgentMeta-agent=GPT-5.4-Nano2026.0652.91
Skill-MAS-optimizedMeta-agent=DeepSeek-V4-Flash2026.0651.69
Skill-MAS-optimizedMeta-agent=Qwen3.5-Plus2026.0651.28
AFlowMeta-agent=DeepSeek-V4-Flash2026.0649.93
EvoAgentMeta-agent=DeepSeek-V4-Flash2026.0649.1
Skill-MAS-optimizedMeta-agent=GPT-5.4-Nano2026.0648.9
Skill-MAS-initMeta-agent=Qwen3.5-Plus2026.0648.88
EvoAgentMeta-agent=Qwen3.5-Plus2026.0647.02
AFlowMeta-agent=Qwen3.5-Plus2026.0646.17
Skill-MAS-initMeta-agent=DeepSeek-V4-Flash2026.0644.99
Skill-MAS-optimizedMeta-agent=Gemini-3.1-Flash2026.0644.71
AOrchestraMeta-agent=GPT-5.4-Nano2026.0644.68
AFlowMeta-agent=GPT-5.4-Nano2026.0644.29
AOrchestraMeta-agent=Qwen3.5-Plus2026.0644.05
MAS-OrchestraMeta-agent=GPT-5.4-Nano2026.0643.83
MAS2Meta-agent=GPT-5.4-Nano2026.0643.2
AFlowMeta-agent=Gemini-3.1-Flash2026.0642.31
AOrchestraMeta-agent=DeepSeek-V4-Flash2026.0641.03
MAS2Meta-agent=Qwen3.5-Plus2026.0640.87
EvoAgentMeta-agent=Gemini-3.1-Flash2026.0640.76
MAS-OrchestraMeta-agent=DeepSeek-V4-Flash2026.0640.63
Skill-MAS-initMeta-agent=GPT-5.4-Nano2026.0640.45
MAS-OrchestraMeta-agent=Qwen3.5-Plus2026.0640.43
MAS-OrchestraMeta-agent=Gemini-3.1-Flash2026.0640.4
AOrchestraMeta-agent=Gemini-3.1-Flash2026.0639.49
MAS2Meta-agent=Gemini-3.1-Flash2026.0638.03
Skill-MAS-initMeta-agent=Gemini-3.1-Flash2026.0636.1
MAS2Meta-agent=DeepSeek-V4-Flash2026.0635.31