Rank #8 on AIDB
9 models in the AIDB database. Average AIDB score 89, top score 91, momentum index 135.2.
DeepSeek's language model tracked by Epoch, focused on mathematical reasoning.
DeepSeek's language model tracked by Epoch, focused on language modeling/generation.
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
Open reasoning model trained with RL, competitive with o1-class systems.
DeepSeek's language model tracked by Epoch, focused on language modeling/generation.
High-performance open MoE LLM rivaling closed frontier models on benchmarks.
We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
DeepSeek's language model tracked by Epoch, focused on language modeling/generation.