DeepSeek open-sourced DeepSeek-R1, wakewiki.de an LLM fine-tuned with learning (RL) to improve thinking capability. DeepSeek-R1 attains outcomes on par with OpenAI’s o1 model on numerous benchmarks, consisting of MATH-500 and SWE-bench.

DeepSeek-R1 is based upon DeepSeek-V3, a mixture of professionals (MoE) design recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented version of RL. The research group likewise performed understanding distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched several versions of each