General AI Assistant tasks on GAIA (Pass@1, Pass@3)
83.4Pass@1 ScoreAgentOrchestra
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AgentOrchestra2026.05 | 83.4 | — | |
| Uno-Orchestra2026.05 | 82 | — | |
| Tongyi DeepResearchAgent Type=DeepResearch Agent, Configuration=30B-A3B2025.10 | 70.9 | — | |
| OpenAI-o3Paradigm=ReAct, Summary Tool=-2025.09 | 70.5 | — | |
| AOrchestra2026.05 | 69.4 | — | |
| Claude-4Paradigm=ReAct, Summary Tool=-2025.09 | 68.3 | — | |
| Claude-4-SonnetAgent Type=LLM-based ReAct Agent2025.10 | 68.3 | — | |
| OpenAI DeepResearchAgent Type=DeepResearch Agent2025.10 | 67.4 | — | |
| GLM 4.5Agent Type=LLM-based ReAct Agent2025.10 | 66 | — | |
| DeepSeek-v3.1Paradigm=ReAct, Summary Tool=-2025.09 | 63.1 | — | |
| DeepSeek-V3.1Agent Type=LLM-based ReAct Agent2025.10 | 63.1 | — | |
| OpenAI o4-miniAgent Type=LLM-based ReAct Agent2025.10 | 60 | — | |
| Kimi-K2Paradigm=ReAct, Summary Tool=-2025.09 | 57.7 | — | |
| Kimi K2Agent Type=LLM-based ReAct Agent2025.10 | 57.7 | — | |
| WebSailor-30BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.09 | 51.5 | 68.9 | |
| WebSailor-30BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.09 | 49.2 | 71.8 | |
| WebSailor-30BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.09 | 47.3 | 63.1 | |
| WebSailor-30BParadigm=ReSum, Summary Tool=Qwen3-235B2025.09 | 46.9 | 67 | |
| WebSailor-30BParadigm=ReSum, Summary Tool=Qwen3-30B2025.09 | 45.6 | 61.2 | |
| WebSailor-30BParadigm=ReAct, Summary Tool=-2025.09 | 45 | 60.2 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=Qwen3-235B2025.09 | 43.4 | 60.2 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.09 | 42.4 | 61.2 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.09 | 41.1 | 58.3 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.09 | 40.5 | 65.1 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.09 | 40.5 | 60.2 | |
| WebSailor-30BParadigm=Recent History, Summary Tool=-2025.09 | 40.1 | 56.3 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.09 | 39.2 | 60.2 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.09 | 35.3 | 52.4 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=Qwen3-30B2025.09 | 34.6 | 48.5 | |
| WebSailor-30BParadigm=MEM1, Summary Tool=-2025.09 | 33.3 | 52.4 | |
| WebSailor-7BParadigm=Recent History, Summary Tool=-2025.09 | 33 | 48.5 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=Qwen3-235B2025.09 | 32.4 | 49.5 | |
| WebSailor-7BParadigm=ReAct, Summary Tool=-2025.09 | 31.7 | 44.7 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=Qwen3-30B2025.09 | 27.5 | 45.6 | |
| WebSailor-3BParadigm=Recent History, Summary Tool=-2025.09 | 27.2 | 44.7 | |
| WebSailor-3BParadigm=ReAct, Summary Tool=-2025.09 | 25.6 | 42.7 | |
| xRouter2026.05 | 24.8 | — | |
| ColdStart-LLM2026.05 | 17.2 | — |