General AI Assistant on GAIA
40.8GAIA (WS)TOOLSELF
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TOOLSELFBase Model=Qwen3-14B2026.02 | 40.8 | 38.8 | |
| OWLBase Model=Qwen3-14B2026.02 | 36.9 | 29.2 | |
| ReSumBase Model=Qwen3-14B2026.02 | 35.9 | — | |
| WebSailorBase Model=Qwen3-14B2026.02 | 35 | — | |
| Vanilla AgentBase Model=Qwen3-14B2026.02 | 33 | 32.1 | |
| Co-SightBase Model=Qwen3-14B2026.02 | 31.1 | — | |
| OAgentsBase Model=Qwen3-14B2026.02 | 30.1 | — | |
| TOOLSELFBase Model=Qwen3-8B2026.02 | 30.1 | 27.9 | |
| Co-SightBase Model=Qwen3-8B2026.02 | 28.1 | — | |
| ReSumBase Model=Qwen3-8B2026.02 | 27.2 | — | |
| OWLBase Model=Qwen3-8B2026.02 | 23.3 | 21.8 | |
| OAgentsBase Model=Qwen3-8B2026.02 | 22.3 | — | |
| Vanilla AgentBase Model=Qwen3-8B2026.02 | 19.4 | 19.7 | |
| WebSailorBase Model=Qwen3-8B2026.02 | 18.5 | — | |
| GPT-52026.05 | — | 76.4 | |
| OpenAI-DR2026.05 | — | 67.4 | |
| OpenResearcher2026.05 | — | 64.1 | |
| Quest-30B2026.05 | — | 69 | |
| Quest-35B2026.05 | — | 80.8 | |
| Tongyi-DR2026.05 | — | 70.9 |