List your company

Embodied Agentic on GAIA

0.672AccuracyM2CL
0.135360.274680.4140.55332Feb 2, 2026

Evaluation results

MethodLinks
M2CLBackbone Model=Qwen-72B, Number of LLMs=42026.020.672
MacNetBackbone Model=Qwen-72B, Number of LLMs=42026.020.464
DebateBackbone Model=Qwen-72B, Number of LLMs=42026.020.429
M2CLBackbone Model=Qwen-14B, Number of LLMs=42026.020.42
Best-of-N (BoN)Backbone Model=Qwen-72B, Number of LLMs=42026.020.412
DyLANBackbone Model=Qwen-72B, Number of LLMs=42026.020.404
GPTSwarmBackbone Model=Qwen-72B, Number of LLMs=42026.020.403
M2CLBackbone Model=Qwen-7B, Number of LLMs=42026.020.336
MacNetBackbone Model=Qwen-14B, Number of LLMs=42026.020.322
Single executionBackbone Model=Qwen-72B, Number of LLMs=42026.020.311
DebateBackbone Model=Qwen-14B, Number of LLMs=42026.020.264
Best-of-N (BoN)Backbone Model=Qwen-14B, Number of LLMs=42026.020.256
GPTSwarmBackbone Model=Qwen-14B, Number of LLMs=42026.020.25
DyLANBackbone Model=Qwen-14B, Number of LLMs=42026.020.228
MacNetBackbone Model=Qwen-7B, Number of LLMs=42026.020.215
Best-of-N (BoN)Backbone Model=Qwen-7B, Number of LLMs=42026.020.211
DebateBackbone Model=Qwen-7B, Number of LLMs=42026.020.21
GPTSwarmBackbone Model=Qwen-7B, Number of LLMs=42026.020.206
Single executionBackbone Model=Qwen-14B, Number of LLMs=42026.020.187
DyLANBackbone Model=Qwen-7B, Number of LLMs=42026.020.184
Single executionBackbone Model=Qwen-7B, Number of LLMs=42026.020.156