DeepSeek open-sourced DeepSeek-R1, higgledy-piggledy.xyz an LLM fine-tuned with support knowing (RL) to enhance thinking capability. DeepSeek-R1 attains results on par with OpenAI’s o1 design on numerous criteria, including MATH-500 and SWE-bench.

DeepSeek-R1 is based upon DeepSeek-V3, a mix of professionals (MoE) model recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy (GRPO), a reasoning-oriented version of RL. The research group also performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and released several variations of each