Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-agent Debate on MMLU-Pro Debate

65.7Success Rate (SR)

Concise

51.45255.15158.8562.549Apr 7, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.04
65.7847
2026.04
65.7806
2026.04
65.31,707
2026.04
64.71,617
2026.04
62.31,617
2026.04
58.3782
2026.04
53.71,531
2026.04
53.71,690
2026.04
52.3829
2026.04
521,531