List your company

Multi-agent Debate on MMLU-Pro Debate

65.7Success Rate (SR)Concise
51.45255.15158.8562.549Apr 7, 2026

Evaluation results

MethodLinks
ConciseListener=Llama-70B2026.0465.7847
HANDRAISERListener=Llama-70B2026.0465.7806
PromptingListener=Llama-70B2026.0465.31,707
GenericListener=Llama-70B2026.0464.71,617
RandomListener=Llama-70B2026.0462.31,617
HANDRAISERListener=Llama-8B2026.0458.3782
RandomListener=Llama-8B2026.0453.71,531
PromptingListener=Llama-8B2026.0453.71,690
ConciseListener=Llama-8B2026.0452.3829
GenericListener=Llama-8B2026.04521,531