Skywork/Skywork-OR1-Math-7B

8B • Updated May 29 • 2.09k • 11

Note Specifically optimized for mathematical reasoning, scoring 69.8 on AIME24 and 52.3 on AIME25

Skywork/Skywork-OR1-32B-Preview

33B • Updated May 29 • 1.85k • 68

Note Delivers the 671B-parameter Deepseek-R1 performance on math tasks (AIME24 and AIME25) and coding tasks (LiveCodeBench)

Skywork/Skywork-OR1-7B-Preview

8B • Updated May 29 • 2.14k • 13

Note Outperforms all similarly sized models in both math and coding scenarios

Note Aa dataset of 110K verifiable, challenging, and diverse math problems and 14K coding questions, with difficulty estimation labels