Embodied Agentic on SciWorld
88.9AccuracyM2CL
Evaluation Results
| Method | Links | |
|---|---|---|
| M2CLBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 88.9 | |
| MacNetBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 68.4 | |
| DebateBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 65.2 | |
| Best-of-N (BoN)Backbone Model=Qwen-72B, Number of LLMs=42026.02 | 62.1 | |
| GPTSwarmBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 60.2 | |
| DyLANBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 58 | |
| M2CLBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 56.1 | |
| Single executionBackbone Model=Qwen-72B, Number of LLMs=42026.02 | 50.4 | |
| MacNetBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 46 | |
| M2CLBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 45.3 | |
| Best-of-N (BoN)Backbone Model=Qwen-14B, Number of LLMs=42026.02 | 41.6 | |
| DebateBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 39.4 | |
| MacNetBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 37 | |
| DyLANBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 36 | |
| GPTSwarmBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 35.9 | |
| Best-of-N (BoN)Backbone Model=Qwen-7B, Number of LLMs=42026.02 | 35.3 | |
| DebateBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 32.2 | |
| Single executionBackbone Model=Qwen-14B, Number of LLMs=42026.02 | 31.3 | |
| GPTSwarmBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 30.8 | |
| DyLANBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 29.4 | |
| Single executionBackbone Model=Qwen-7B, Number of LLMs=42026.02 | 25.2 |