Deepseek R1

DeepSeek's flagship 671B reasoning model with chain-of-thought, matching o1 performance on math and coding benchmarks.

DeepSeek's May 2025 R1 update — stronger reasoning across math, coding, and science over the original R1 release.

DeepSeek's pure-RL reasoning model trained without SFT — demonstrates emergent chain-of-thought through reinforcement learning alone.