Research Papers Institution
A Chinese AI lab known for strong open-weight language and reasoning models.
DeepSeek-V4 ships two MoE models, 1.6T/49B and 284B/13B, with compressed sparse plus heavily compressed attention that cuts 1M-context KV cache to 10% of V3.2, mHC residuals and Muon.
DeepSeekMath 7B reached 51.7% on MATH with no tools or voting by pretraining on 120B web math tokens and then running GRPO, a PPO variant that deletes the value model and scores answers against their own sampling group.
AI Theorem Proving Papers · DeepSeek
DeepSeek-Prover-V1.5 combines Lean feedback, reinforcement learning, and RMaxTS search, reaching 63.5% on miniF2F and 25.3% on ProofNet.
DeepSeek-V3 is a 671B-parameter MoE model that activates only 37B params per token, matches leading closed models on many benchmarks, and was pre-trained on 14.8T tokens for just 2.788M H800 GPU hours with open weights.
DeepSeek-R1 learns to reason from reinforcement learning on whether its answer is correct — with no human reasoning examples — matches OpenAI o1 on AIME and MATH-500, and ships open MIT-licensed weights.