List your company

General AI Assistant tasks on GAIA (Pass@1, Pass@3)

83.4Pass@1 ScoreAgentOrchestra
14.55232.42650.368.174Sep 16, 2025Oct 24, 2025Dec 2, 2025Jan 10, 2026Feb 17, 2026Mar 28, 2026May 6, 2026

Evaluation results

MethodLinks
AgentOrchestra2026.0583.4—
Uno-Orchestra2026.0582—
Tongyi DeepResearchAgent Type=DeepResearch Agent, Configuration=30B-A3B2025.1070.9—
OpenAI-o3Paradigm=ReAct, Summary Tool=-2025.0970.5—
AOrchestra2026.0569.4—
Claude-4Paradigm=ReAct, Summary Tool=-2025.0968.3—
Claude-4-SonnetAgent Type=LLM-based ReAct Agent2025.1068.3—
OpenAI DeepResearchAgent Type=DeepResearch Agent2025.1067.4—
GLM 4.5Agent Type=LLM-based ReAct Agent2025.1066—
DeepSeek-v3.1Paradigm=ReAct, Summary Tool=-2025.0963.1—
DeepSeek-V3.1Agent Type=LLM-based ReAct Agent2025.1063.1—
OpenAI o4-miniAgent Type=LLM-based ReAct Agent2025.1060—
Kimi-K2Paradigm=ReAct, Summary Tool=-2025.0957.7—
Kimi K2Agent Type=LLM-based ReAct Agent2025.1057.7—
WebSailor-30BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.0951.568.9
WebSailor-30BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.0949.271.8
WebSailor-30BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.0947.363.1
WebSailor-30BParadigm=ReSum, Summary Tool=Qwen3-235B2025.0946.967
WebSailor-30BParadigm=ReSum, Summary Tool=Qwen3-30B2025.0945.661.2
WebSailor-30BParadigm=ReAct, Summary Tool=-2025.094560.2
WebSailor-7BParadigm=ReSum, Summary Tool=Qwen3-235B2025.0943.460.2
WebSailor-7BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.0942.461.2
WebSailor-7BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.0941.158.3
WebSailor-3BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.0940.565.1
WebSailor-7BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.0940.560.2
WebSailor-30BParadigm=Recent History, Summary Tool=-2025.0940.156.3
WebSailor-3BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.0939.260.2
WebSailor-3BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.0935.352.4
WebSailor-7BParadigm=ReSum, Summary Tool=Qwen3-30B2025.0934.648.5
WebSailor-30BParadigm=MEM1, Summary Tool=-2025.0933.352.4
WebSailor-7BParadigm=Recent History, Summary Tool=-2025.093348.5
WebSailor-3BParadigm=ReSum, Summary Tool=Qwen3-235B2025.0932.449.5
WebSailor-7BParadigm=ReAct, Summary Tool=-2025.0931.744.7
WebSailor-3BParadigm=ReSum, Summary Tool=Qwen3-30B2025.0927.545.6
WebSailor-3BParadigm=Recent History, Summary Tool=-2025.0927.244.7
WebSailor-3BParadigm=ReAct, Summary Tool=-2025.0925.642.7
xRouter2026.0524.8—
ColdStart-LLM2026.0517.2—