List your company

Mathematical Reasoning on AIME25 decontaminated (Accuracy)

22.6AccuracyDAPO++
1.4886.96912.4517.931May 26, 2026

Evaluation results

MethodLinks
DAPO++Backbone=Qwen3-8B, Sampling Strategy=Mean@322026.0522.6
DAPO-Math-17kBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0521.5
DeepScaleRBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0517.1
DeepMath-103KBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0516.7
Skywork-OR1-RL-DataBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0515.8
OpenR1-Math-220kBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0515.4
Qwen3-8B-BaseBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0510.5
DeepScaleRBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.057.6
OpenR1-Math-220kBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.056.3
DAPO-Math-17kBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.055.9
Skywork-OR1-RL-DataBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.054.6
DAPO++Backbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.053.3
DeepMath-103KBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.053.1
Qwen3-1.7B-BaseBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.052.3