Skywork/Skywork-OR1-32B
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:May 13, 2025Architecture:Transformer0.0K Cold

Skywork/Skywork-OR1-32B is a 32.8 billion parameter open reasoner model developed by Skywork, specializing in advanced math and code reasoning tasks. Trained using large-scale rule-based reinforcement learning, it features a 131072 token context length. This model demonstrates strong performance in mathematical problem-solving (AIME24, AIME25) and coding challenges (LiveCodeBench), outperforming several similarly sized models in these domains. It is primarily designed for applications requiring robust analytical and logical deduction capabilities in technical fields.

Loading preview...