List your company

Mathematical Reasoning on AMC23 decontaminated (Accuracy)

69.8AccuracyDAPO-Math-17k
26.53637.7684960.232May 26, 2026

Evaluation results

MethodLinks
DAPO-Math-17kBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0569.8
DAPO++Backbone=Qwen3-8B, Sampling Strategy=Mean@322026.0569.3
Skywork-OR1-RL-DataBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0564.1
OpenR1-Math-220kBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0563.2
DeepMath-103KBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0562.7
DeepScaleRBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0561.6
Qwen3-8B-BaseBackbone=Qwen3-8B, Sampling Strategy=Mean@322026.0548.6
DAPO++Backbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.0541.9
Skywork-OR1-RL-DataBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.0540.9
DAPO-Math-17kBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.0539.5
DeepMath-103KBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.0535.4
DeepScaleRBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.0534.5
OpenR1-Math-220kBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.0531.6
Qwen3-1.7B-BaseBackbone=Qwen3-1.7B, Sampling Strategy=Mean@322026.0528.2