List your company

Mathematical Reasoning on AIME 24 (Maj, Debate, Delta)

30.8Maj ScoreSDRL-rand
6.3612.70519.0525.395Jan 29, 2026

Evaluation results

MethodLinks
SDRL-randBackbone=Qwen3-4B-Base, Debate system agents (N)=5, Debate rounds=12026.0130.831.70.9
SDRL-freqBackbone=Qwen3-4B-Base, Debate system agents (N)=5, Debate rounds=12026.0128.7367.3
DAPOBackbone=Qwen3-4B-Base, Debate system agents (N)=5, Debate rounds=12026.0126.728.31.6
SDRL-freqBackbone=Qwen2.5-3B, Debate system agents (N)=5, Debate rounds=12026.019.313.34
SDRL-randBackbone=Qwen2.5-3B, Debate system agents (N)=5, Debate rounds=12026.018.711.73
DAPOBackbone=Qwen2.5-3B, Debate system agents (N)=5, Debate rounds=12026.017.3102.7