List your company
ResearchFormerly WizWand

Mathematical Reasoning on AIME 25 (Peak Accuracy)

27.5Peak Accuracy14B-PC
13.77217.33620.924.464May 26, 2026
Updated 5mo ago

Evaluation results

MethodLinks
14B-PCModel Scale=14B, RL Algorithm=PC, Rollouts Trained=2,048, Rollouts Sampled=4,0962026.0527.5
14B-GRPOModel Scale=14B, RL Algorithm=GRPO, Rollouts Trained=2,048, Rollouts Sampled=2,0482026.0523.6
14B-DAPOModel Scale=14B, RL Algorithm=DAPO, Rollouts Trained=2,048, Rollouts Sampled=6,1442026.0521.9
8B-PCModel Scale=8B, RL Algorithm=PC, Rollouts Trained=2,048, Rollouts Sampled=4,0962026.0521.4
8B-DAPOModel Scale=8B, RL Algorithm=DAPO, Rollouts Trained=2,048, Rollouts Sampled=6,1442026.0520.8
4B-PCModel Scale=4B, RL Algorithm=PC, Rollouts Trained=2,048, Rollouts Sampled=4,0962026.0519.6
4B-DAPOModel Scale=4B, RL Algorithm=DAPO, Rollouts Trained=2,048, Rollouts Sampled=6,1442026.0519.1
4B-GRPOModel Scale=4B, RL Algorithm=GRPO, Rollouts Trained=2,048, Rollouts Sampled=2,0482026.0517.4
8B-GRPOModel Scale=8B, RL Algorithm=GRPO, Rollouts Trained=2,048, Rollouts Sampled=2,0482026.0516.6
1.5B-PCModel Scale=1.5B, RL Algorithm=PC, Rollouts Trained=2,048, Rollouts Sampled=4,0962026.0515.3
1.5B-DAPOModel Scale=1.5B, RL Algorithm=DAPO, Rollouts Trained=2,048, Rollouts Sampled=6,1442026.0514.5
1.5B-GRPOModel Scale=1.5B, RL Algorithm=GRPO, Rollouts Trained=2,048, Rollouts Sampled=2,0482026.0514.3