Embodied Agentic on GAIA
0.672AccuracyM2CL
Evaluation Results
| Method | Links | |
|---|---|---|
| M2CLBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 0.672 | |
| MacNetBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 0.464 | |
| DebateBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 0.429 | |
| M2CLBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 0.42 | |
| Best-of-N (BoN)Backbone Model=Qwen-72B, Number of LLMs=42026.02 | 0.412 | |
| DyLANBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 0.404 | |
| GPTSwarmBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 0.403 | |
| M2CLBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 0.336 | |
| MacNetBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 0.322 | |
| Single executionBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 0.311 | |
| DebateBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 0.264 | |
| Best-of-N (BoN)Backbone Model=Qwen-14B, Number of LLMs=42026.02 | 0.256 | |
| GPTSwarmBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 0.25 | |
| DyLANBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 0.228 | |
| MacNetBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 0.215 | |
| Best-of-N (BoN)Backbone Model=Qwen-7B, Number of LLMs=42026.02 | 0.211 | |
| DebateBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 0.21 | |
| GPTSwarmBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 0.206 | |
| Single executionBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 0.187 | |
| DyLANBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 0.184 | |
| Single executionBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 0.156 |