↓ Skip to main content

“Notably, it is the first open research to validate that reasoning capabilities of LLMs can be incentivized purely through RL, without the need for SFT.”

DeepSeekgithub.com ↗

DeepSeek released R1 with weights under the MIT license. It matches o1 on AIME 2024, 79.8% to 79.2%. Distilled versions run on Qwen and Llama bases on ordinary hardware. OpenAI’s paid reasoning tier now has a free competitor.