List your company

Mathematical Reasoning on AMC 23 (Maj, Debate, Delta)

73MajDAPO
48.0454.526167.48Jan 29, 2026

Evaluation results

MethodLinks
DAPOBackbone=Qwen3-4B-Base, Debate system agents (N)=5, Debate rounds=12026.0173763
SDRL-randBackbone=Qwen3-4B-Base, Debate system agents (N)=5, Debate rounds=12026.0172.5807.5
SDRL-freqBackbone=Qwen3-4B-Base, Debate system agents (N)=5, Debate rounds=12026.0172.5796.5
SDRL-freqBackbone=Qwen2.5-3B, Debate system agents (N)=5, Debate rounds=12026.0152.553.51
SDRL-randBackbone=Qwen2.5-3B, Debate system agents (N)=5, Debate rounds=12026.0149.253.84.6
DAPOBackbone=Qwen2.5-3B, Debate system agents (N)=5, Debate rounds=12026.0149501