Science Simulation on SciWorld (Accuracy)
94.6AccuracyM2CL
Evaluation Results
| Method | Links | |
|---|---|---|
| M2CLModel=Qwen-72B, Number of LLMs=162026.02 | 94.6 | |
| M2CLModel=Llama-70B, Number of LLMs=162026.02 | 81.7 | |
| MacNetModel=Qwen-72B, Number of LLMs=162026.02 | 74.7 | |
| MacNetModel=Llama-70B, Number of LLMs=162026.02 | 70.8 | |
| DebateModel=Qwen-72B, Number of LLMs=162026.02 | 66.7 | |
| BoNModel=Qwen-72B, Number of LLMs=162026.02 | 62.9 | |
| GPTSwarmModel=Qwen-72B, Number of LLMs=162026.02 | 59.8 | |
| M2CLModel=Qwen-14B, Number of LLMs=162026.02 | 59.4 | |
| DyLANModel=Qwen-72B, Number of LLMs=162026.02 | 59.1 | |
| DebateModel=Llama-70B, Number of LLMs=162026.02 | 51.2 | |
| SingleModel=Qwen-72B, Number of LLMs=12026.02 | 50.1 | |
| BoNModel=Llama-70B, Number of LLMs=162026.02 | 49.8 | |
| MacNetModel=Qwen-14B, Number of LLMs=162026.02 | 49.3 | |
| M2CLModel=Qwen-7B, Number of LLMs=162026.02 | 47.6 | |
| GPTSwarmModel=Llama-70B, Number of LLMs=162026.02 | 47.5 | |
| M2CLModel=Llama-14B, Number of LLMs=162026.02 | 47.1 | |
| DyLANModel=Llama-70B, Number of LLMs=162026.02 | 46.8 | |
| BoNModel=Qwen-14B, Number of LLMs=162026.02 | 42.3 | |
| DebateModel=Qwen-14B, Number of LLMs=162026.02 | 40.5 | |
| MacNetModel=Qwen-7B, Number of LLMs=162026.02 | 39.7 | |
| M2CLModel=Llama-7B, Number of LLMs=162026.02 | 38.4 | |
| SingleModel=Llama-70B, Number of LLMs=12026.02 | 38.3 | |
| MacNetModel=Llama-14B, Number of LLMs=162026.02 | 37.8 | |
| GPTSwarmModel=Qwen-14B, Number of LLMs=162026.02 | 36.8 | |
| DyLANModel=Qwen-14B, Number of LLMs=162026.02 | 35.7 | |
| BoNModel=Qwen-7B, Number of LLMs=162026.02 | 35.4 | |
| BoNModel=Llama-14B, Number of LLMs=162026.02 | 33.5 | |
| MacNetModel=Llama-7B, Number of LLMs=162026.02 | 33.4 | |
| DebateModel=Qwen-7B, Number of LLMs=162026.02 | 32.6 | |
| DebateModel=Llama-14B, Number of LLMs=162026.02 | 30.9 | |
| SingleModel=Qwen-14B, Number of LLMs=12026.02 | 30.9 | |
| GPTSwarmModel=Qwen-7B, Number of LLMs=162026.02 | 30.4 | |
| DyLANModel=Llama-14B, Number of LLMs=162026.02 | 30.2 | |
| DyLANModel=Qwen-7B, Number of LLMs=162026.02 | 28.7 | |
| GPTSwarmModel=Llama-7B, Number of LLMs=162026.02 | 26.8 | |
| BoNModel=Llama-7B, Number of LLMs=162026.02 | 25.7 | |
| DebateModel=Llama-7B, Number of LLMs=162026.02 | 25.3 | |
| SingleModel=Qwen-7B, Number of LLMs=12026.02 | 24.9 | |
| SingleModel=Llama-14B, Number of LLMs=12026.02 | 24 | |
| DyLANModel=Llama-7B, Number of LLMs=162026.02 | 22.7 | |
| SingleModel=Llama-7B, Number of LLMs=12026.02 | 19.6 |