List your company

Mathematical Reasoning on Minerva decontaminated (Accuracy)

37.1AccuracyDAPO++
14.42820.31426.232.086May 26, 2026

Evaluation results

MethodLinks
DAPO++Backbone=Qwen3-8B, Sampling Strategy=Mean@42026.0537.1
DAPO-Math-17kBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0536.7
OpenR1-Math-220kBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0535.7
DeepScaleRBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0534.7
Skywork-OR1-RL-DataBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0534.5
DeepMath-103KBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0531.9
DeepMath-103KBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0526.5
Qwen3-8B-BaseBackbone=Qwen3-8B, Sampling Strategy=Mean@42026.0525.6
DeepScaleRBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0523.3
OpenR1-Math-220kBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0523.1
Skywork-OR1-RL-DataBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0522.8
DAPO-Math-17kBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0522.6
DAPO++Backbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0521.9
Qwen3-1.7B-BaseBackbone=Qwen3-1.7B, Sampling Strategy=Mean@42026.0515.3