DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to improve thinking ability. DeepSeek-R1 attains results on par with OpenAI’s o1 model on several standards, including MATH-500 and SWE-bench.

DeepSeek-R1 is based upon DeepSeek-V3, trademarketclassifieds.com a mixture of professionals (MoE) model just recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy Optimization (GRPO), hb9lc.org a reasoning-oriented variant of RL. The research study group likewise performed knowledge distillation from DeepSeek-R1 to open-source Qwen and ratemywifey.com Llama models and released several variations of each