List your company

Mathematical Reasoning on MATH 500 (Maj, Debate, Delta)

88.8Maj ScoreSDRL-rand
69.97674.86379.7584.637Jan 29, 2026

Evaluation results

MethodLinks
SDRL-randBackbone=Qwen3-4B-Base, Debate system agents (N)=5, Debate rounds=12026.0188.886.6-2.2
SDRL-freqBackbone=Qwen3-4B-Base, Debate system agents (N)=5, Debate rounds=12026.018785.9-1.1
DAPOBackbone=Qwen3-4B-Base, Debate system agents (N)=5, Debate rounds=12026.0186.983.1-3.8
SDRL-freqBackbone=Qwen2.5-3B, Debate system agents (N)=5, Debate rounds=12026.0171.471.70.3
DAPOBackbone=Qwen2.5-3B, Debate system agents (N)=5, Debate rounds=12026.0170.971.10.2
SDRL-randBackbone=Qwen2.5-3B, Debate system agents (N)=5, Debate rounds=12026.0170.771.40.7