Scientific Reasoning on SciWorld (Accuracy)
95.9AccuracyM2CL
Evaluation Results
| Method | Links | |
|---|---|---|
| M2CLModel=Qwen-72B, Number of LLMs=642026.02 | 95.9 | |
| M2CLBackbone=Qwen-72B, Number of LLMs=322026.02 | 95 | |
| M2CLBackbone=Qwen-72B, Number of LLMs=82026.02 | 88.9 | |
| M2CLModel=Llama-70B, Number of LLMs=642026.02 | 88.9 | |
| M2CLBackbone=Llama-70B, Number of LLMs=322026.02 | 86 | |
| MacNetModel=Qwen-72B, Number of LLMs=642026.02 | 85.1 | |
| M2CLBase Model=Qwen-72B, Number of LLMs=42026.02 | 81.9 | |
| MacNetModel=Llama-70B, Number of LLMs=642026.02 | 81.6 | |
| MacNetBackbone=Qwen-72B, Number of LLMs=322026.02 | 79.5 | |
| MacNetBackbone=Llama-70B, Number of LLMs=322026.02 | 76.6 | |
| M2CLBackbone=Llama-70B, Number of LLMs=82026.02 | 76.2 | |
| DebateModel=Qwen-72B, Number of LLMs=642026.02 | 69.1 | |
| MacNetBackbone=Qwen-72B, Number of LLMs=82026.02 | 68.4 | |
| DebateBackbone=Qwen-72B, Number of LLMs=322026.02 | 67.8 | |
| BoNModel=Qwen-72B, Number of LLMs=642026.02 | 66 | |
| M2CLModel=Qwen-14B, Number of LLMs=642026.02 | 65.8 | |
| M2CLBase Model=Llama-70B, Number of LLMs=42026.02 | 65.5 | |
| DebateBackbone=Qwen-72B, Number of LLMs=82026.02 | 65.2 | |
| MacNetBase Model=Qwen-72B, Number of LLMs=42026.02 | 64.1 | |
| MacNetBackbone=Llama-70B, Number of LLMs=82026.02 | 64 | |
| GPTSwarmModel=Qwen-72B, Number of LLMs=642026.02 | 63.2 | |
| BoNBackbone=Qwen-72B, Number of LLMs=322026.02 | 63.2 | |
| GPTSwarmBackbone=Qwen-72B, Number of LLMs=322026.02 | 62.6 | |
| DebateBase Model=Qwen-72B, Number of LLMs=42026.02 | 62.5 | |
| BoNBackbone=Qwen-72B, Number of LLMs=82026.02 | 62.1 | |
| M2CLBackbone=Qwen-14B, Number of LLMs=322026.02 | 62.1 | |
| GPTSwarmBackbone=Qwen-72B, Number of LLMs=82026.02 | 60.2 | |
| DyLANModel=Qwen-72B, Number of LLMs=642026.02 | 59.9 | |
| BoNBase Model=Qwen-72B, Number of LLMs=42026.02 | 59.8 | |
| DyLANBackbone=Qwen-72B, Number of LLMs=322026.02 | 59.1 | |
| GPTSwarmBase Model=Qwen-72B, Number of LLMs=42026.02 | 59.1 | |
| DyLANBackbone=Qwen-72B, Number of LLMs=82026.02 | 58 | |
| DyLANBase Model=Qwen-72B, Number of LLMs=42026.02 | 57.8 | |
| MacNetModel=Qwen-14B, Number of LLMs=642026.02 | 56.8 | |
| M2CLBackbone=Qwen-14B, Number of LLMs=82026.02 | 56.1 | |
| MacNetBase Model=Llama-70B, Number of LLMs=42026.02 | 55.9 | |
| MacNetBackbone=Qwen-14B, Number of LLMs=322026.02 | 54.2 | |
| DebateModel=Llama-70B, Number of LLMs=642026.02 | 53.5 | |
| M2CLModel=Qwen-7B, Number of LLMs=642026.02 | 53.3 | |
| M2CLModel=Llama-14B, Number of LLMs=642026.02 | 52.8 | |
| DebateBackbone=Llama-70B, Number of LLMs=322026.02 | 52.1 | |
| M2CLBase Model=Qwen-14B, Number of LLMs=42026.02 | 51.3 | |
| SingleBase Model=Qwen-72B, Number of LLMs=12026.02 | 51.1 | |
| BoNModel=Llama-70B, Number of LLMs=642026.02 | 51 | |
| M2CLBackbone=Llama-14B, Number of LLMs=322026.02 | 50.7 | |
| SingleBackbone=Qwen-72B, Number of LLMs=82026.02 | 50.4 | |
| M2CLBackbone=Qwen-7B, Number of LLMs=322026.02 | 50.4 | |
| DebateBackbone=Llama-70B, Number of LLMs=82026.02 | 50.1 | |
| BoNBackbone=Llama-70B, Number of LLMs=322026.02 | 50.1 | |
| GPTSwarmModel=Llama-70B, Number of LLMs=642026.02 | 49.3 | |
| SingleBackbone=Qwen-72B, Number of LLMs=322026.02 | 49 | |
| BoNBackbone=Llama-70B, Number of LLMs=82026.02 | 48.8 | |
| GPTSwarmBackbone=Llama-70B, Number of LLMs=322026.02 | 48.4 | |
| SingleModel=Qwen-72B, Number of LLMs=642026.02 | 48.3 | |
| DebateBase Model=Llama-70B, Number of LLMs=42026.02 | 47.8 | |
| DyLANModel=Llama-70B, Number of LLMs=642026.02 | 47.6 | |
| DyLANBackbone=Llama-70B, Number of LLMs=322026.02 | 47.2 | |
| MacNetModel=Qwen-7B, Number of LLMs=642026.02 | 46.7 | |
| BoNBase Model=Llama-70B, Number of LLMs=42026.02 | 46.7 | |
| GPTSwarmBackbone=Llama-70B, Number of LLMs=82026.02 | 46.5 | |
| DyLANBackbone=Llama-70B, Number of LLMs=82026.02 | 46.4 | |
| MacNetBackbone=Qwen-14B, Number of LLMs=82026.02 | 46 | |
| BoNModel=Qwen-14B, Number of LLMs=642026.02 | 45.6 | |
| M2CLBackbone=Qwen-7B, Number of LLMs=82026.02 | 45.3 | |
| GPTSwarmBase Model=Llama-70B, Number of LLMs=42026.02 | 45.2 | |
| BoNBackbone=Qwen-14B, Number of LLMs=322026.02 | 45.1 | |
| DyLANBase Model=Llama-70B, Number of LLMs=42026.02 | 45.1 | |
| M2CLBackbone=Llama-14B, Number of LLMs=82026.02 | 44.7 | |
| MacNetModel=Llama-14B, Number of LLMs=642026.02 | 44.4 | |
| MacNetBackbone=Qwen-7B, Number of LLMs=322026.02 | 43.1 | |
| M2CLModel=Llama-7B, Number of LLMs=642026.02 | 42.9 | |
| DebateModel=Qwen-14B, Number of LLMs=642026.02 | 42.7 | |
| MacNetBackbone=Llama-14B, Number of LLMs=322026.02 | 41.7 | |
| DebateBackbone=Qwen-14B, Number of LLMs=322026.02 | 41.7 | |
| M2CLBase Model=Qwen-7B, Number of LLMs=42026.02 | 41.7 | |
| BoNBackbone=Qwen-14B, Number of LLMs=82026.02 | 41.6 | |
| MacNetBase Model=Qwen-14B, Number of LLMs=42026.02 | 41.4 | |
| M2CLBackbone=Llama-7B, Number of LLMs=322026.02 | 40.7 | |
| SingleBase Model=Llama-70B, Number of LLMs=12026.02 | 40.2 | |
| M2CLBase Model=Llama-14B, Number of LLMs=42026.02 | 39.9 | |
| MacNetModel=Llama-7B, Number of LLMs=642026.02 | 39.6 | |
| DebateBackbone=Qwen-14B, Number of LLMs=82026.02 | 39.4 | |
| BoNBase Model=Qwen-14B, Number of LLMs=42026.02 | 39.4 | |
| SingleBackbone=Llama-70B, Number of LLMs=82026.02 | 39.1 | |
| BoNModel=Qwen-7B, Number of LLMs=642026.02 | 38.6 | |
| SingleBackbone=Llama-70B, Number of LLMs=322026.02 | 38.6 | |
| DebateBase Model=Qwen-14B, Number of LLMs=42026.02 | 38.5 | |
| BoNBackbone=Qwen-7B, Number of LLMs=322026.02 | 37.8 | |
| MacNetBackbone=Llama-7B, Number of LLMs=322026.02 | 37.5 | |
| GPTSwarmBackbone=Qwen-14B, Number of LLMs=322026.02 | 37.5 | |
| SingleModel=Llama-70B, Number of LLMs=642026.02 | 37.3 | |
| MacNetBackbone=Qwen-7B, Number of LLMs=82026.02 | 37 | |
| DyLANModel=Qwen-14B, Number of LLMs=642026.02 | 37 | |
| DyLANBackbone=Qwen-14B, Number of LLMs=322026.02 | 36.2 | |
| M2CLBackbone=Llama-7B, Number of LLMs=82026.02 | 36.1 | |
| DyLANBackbone=Qwen-14B, Number of LLMs=82026.02 | 36 | |
| GPTSwarmModel=Qwen-14B, Number of LLMs=642026.02 | 36 | |
| GPTSwarmBackbone=Qwen-14B, Number of LLMs=82026.02 | 35.9 | |
| BoNModel=Llama-14B, Number of LLMs=642026.02 | 35.7 | |
| MacNetBackbone=Llama-14B, Number of LLMs=82026.02 | 35.6 |