List your company

Mathematical Reasoning on Olympiad decontaminated (Accuracy)

43.5AccuracyDAPO++
16.56423.55730.5537.543May 26, 2026

Evaluation results

MethodLinks
DAPO++Backbone=Qwen3-8B, Sampling Strategy=Mean@42026.0543.5
DAPO-Math-17kBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0543
DeepMath-103KBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0539.2
DeepScaleRBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0538.8
Skywork-OR1-RL-DataBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0537.8
OpenR1-Math-220kBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0537
Qwen3-8B-BaseBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0527.9
DAPO++Backbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0524.9
Skywork-OR1-RL-DataBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0524.7
OpenR1-Math-220kBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0524
DeepScaleRBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0523.7
DeepMath-103KBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0523.1
DAPO-Math-17kBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0522.9
Qwen3-1.7B-BaseBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0517.6