Instruction Following on ALFWorld
89.3AccuracyM2CL
Evaluation Results
| Method | Links | |
|---|---|---|
| M2CLBackbone=Qwen-72B, Number of LLMs=322026.02 | 89.3 | |
| M2CLBackbone=Llama-70B, Number of LLMs=322026.02 | 88.5 | |
| M2CLModel=Llama-70B, Number of LLMs=162026.02 | 84.9 | |
| M2CLModel=Qwen-72B, Number of LLMs=162026.02 | 82.9 | |
| MacNetBackbone=Qwen-72B, Number of LLMs=322026.02 | 70.5 | |
| MacNetModel=Qwen-72B, Number of LLMs=162026.02 | 65.8 | |
| MacNetBackbone=Llama-70B, Number of LLMs=322026.02 | 64.5 | |
| DebateBackbone=Qwen-72B, Number of LLMs=322026.02 | 62.8 | |
| MacNetModel=Llama-70B, Number of LLMs=162026.02 | 61.6 | |
| DebateModel=Qwen-72B, Number of LLMs=162026.02 | 60.8 | |
| BoNBackbone=Qwen-72B, Number of LLMs=322026.02 | 59.3 | |
| BoNModel=Qwen-72B, Number of LLMs=162026.02 | 58.5 | |
| GPTSwarmBackbone=Qwen-72B, Number of LLMs=322026.02 | 58.3 | |
| GPTSwarmModel=Qwen-72B, Number of LLMs=162026.02 | 57.3 | |
| DyLANModel=Qwen-72B, Number of LLMs=162026.02 | 56.1 | |
| DyLANBackbone=Qwen-72B, Number of LLMs=322026.02 | 56 | |
| M2CLBackbone=Qwen-14B, Number of LLMs=322026.02 | 54.9 | |
| BoNModel=Llama-70B, Number of LLMs=162026.02 | 53.9 | |
| BoNBackbone=Llama-70B, Number of LLMs=322026.02 | 53.1 | |
| DebateBackbone=Llama-70B, Number of LLMs=322026.02 | 52.6 | |
| DebateModel=Llama-70B, Number of LLMs=162026.02 | 52.2 | |
| M2CLBackbone=Llama-14B, Number of LLMs=322026.02 | 52.2 | |
| GPTSwarmBackbone=Llama-70B, Number of LLMs=322026.02 | 52.2 | |
| GPTSwarmModel=Llama-70B, Number of LLMs=162026.02 | 51.7 | |
| M2CLModel=Qwen-14B, Number of LLMs=162026.02 | 51.2 | |
| DyLANModel=Llama-70B, Number of LLMs=162026.02 | 50.5 | |
| DyLANBackbone=Llama-70B, Number of LLMs=322026.02 | 50.1 | |
| M2CLModel=Llama-14B, Number of LLMs=162026.02 | 48.7 | |
| SingleModel=Qwen-72B, Number of LLMs=12026.02 | 47.7 | |
| SingleBackbone=Qwen-72B, Number of LLMs=322026.02 | 46.7 | |
| MacNetBackbone=Qwen-14B, Number of LLMs=322026.02 | 44.8 | |
| M2CLBackbone=Qwen-7B, Number of LLMs=322026.02 | 44.4 | |
| SingleModel=Llama-70B, Number of LLMs=12026.02 | 43.7 | |
| SingleBackbone=Llama-70B, Number of LLMs=322026.02 | 43.1 | |
| M2CLBackbone=Llama-7B, Number of LLMs=322026.02 | 42.5 | |
| MacNetModel=Qwen-14B, Number of LLMs=162026.02 | 42.1 | |
| M2CLModel=Qwen-7B, Number of LLMs=162026.02 | 41.8 | |
| M2CLModel=Llama-7B, Number of LLMs=162026.02 | 39.8 | |
| DebateBackbone=Qwen-14B, Number of LLMs=322026.02 | 39 | |
| MacNetBackbone=Qwen-7B, Number of LLMs=322026.02 | 38.6 | |
| BoNModel=Qwen-14B, Number of LLMs=162026.02 | 38.1 | |
| DebateModel=Qwen-14B, Number of LLMs=162026.02 | 37.7 | |
| BoNBackbone=Qwen-14B, Number of LLMs=322026.02 | 37.4 | |
| MacNetBackbone=Llama-14B, Number of LLMs=322026.02 | 37.1 | |
| GPTSwarmBackbone=Qwen-14B, Number of LLMs=322026.02 | 36.4 | |
| MacNetBackbone=Llama-7B, Number of LLMs=322026.02 | 35.7 | |
| GPTSwarmModel=Qwen-14B, Number of LLMs=162026.02 | 35.5 | |
| MacNetModel=Qwen-7B, Number of LLMs=162026.02 | 35.4 | |
| DyLANBackbone=Qwen-14B, Number of LLMs=322026.02 | 35.4 | |
| DyLANModel=Qwen-14B, Number of LLMs=162026.02 | 34.9 | |
| MacNetModel=Llama-14B, Number of LLMs=162026.02 | 34.8 | |
| BoNModel=Llama-14B, Number of LLMs=162026.02 | 33 | |
| BoNModel=Qwen-7B, Number of LLMs=162026.02 | 32.9 | |
| MacNetModel=Llama-7B, Number of LLMs=162026.02 | 32.8 | |
| BoNBackbone=Llama-14B, Number of LLMs=322026.02 | 32.8 | |
| BoNBackbone=Qwen-7B, Number of LLMs=322026.02 | 32.8 | |
| DyLANBackbone=Llama-14B, Number of LLMs=322026.02 | 32.1 | |
| DebateModel=Llama-14B, Number of LLMs=162026.02 | 32 | |
| DyLANModel=Llama-14B, Number of LLMs=162026.02 | 31.9 | |
| DebateBackbone=Llama-14B, Number of LLMs=322026.02 | 31.9 | |
| DebateModel=Qwen-7B, Number of LLMs=162026.02 | 31.7 | |
| DebateBackbone=Qwen-7B, Number of LLMs=322026.02 | 31.7 | |
| GPTSwarmBackbone=Qwen-7B, Number of LLMs=322026.02 | 31.2 | |
| DyLANBackbone=Qwen-7B, Number of LLMs=322026.02 | 30.7 | |
| DyLANModel=Qwen-7B, Number of LLMs=162026.02 | 30.4 | |
| GPTSwarmModel=Qwen-7B, Number of LLMs=162026.02 | 30.1 | |
| SingleBackbone=Qwen-14B, Number of LLMs=322026.02 | 29.4 | |
| SingleModel=Qwen-14B, Number of LLMs=12026.02 | 28.3 | |
| SingleModel=Llama-14B, Number of LLMs=12026.02 | 27.4 | |
| GPTSwarmBackbone=Llama-7B, Number of LLMs=322026.02 | 27.3 | |
| GPTSwarmModel=Llama-7B, Number of LLMs=162026.02 | 27.2 | |
| SingleBackbone=Llama-14B, Number of LLMs=322026.02 | 27 | |
| BoNBackbone=Llama-7B, Number of LLMs=322026.02 | 26.8 | |
| BoNModel=Llama-7B, Number of LLMs=162026.02 | 26.7 | |
| DebateBackbone=Llama-7B, Number of LLMs=322026.02 | 26.4 | |
| DebateModel=Llama-7B, Number of LLMs=162026.02 | 25.7 | |
| DyLANBackbone=Llama-7B, Number of LLMs=322026.02 | 24.9 | |
| DyLANModel=Llama-7B, Number of LLMs=162026.02 | 24.6 | |
| SingleBackbone=Qwen-7B, Number of LLMs=322026.02 | 24.2 | |
| SingleModel=Qwen-7B, Number of LLMs=12026.02 | 23.4 | |
| SingleModel=Llama-7B, Number of LLMs=12026.02 | 22.4 | |
| SingleBackbone=Llama-7B, Number of LLMs=322026.02 | 22.4 |