Models

DeepSeek Janus: The Unified Multimodal Model, Tested and Explained2026-04-25 DeepSeek V2.5 Explained: Specs, Benchmarks and What Replaced It2026-04-25 DeepSeek Prover: The Open-Source Lean 4 Theorem-Proving Model2026-04-25 What DeepSeek MoE Is and Why It Powers V4-Pro and V4-Flash2026-04-25 DeepSeek LLM Explained: Architecture, Benchmarks and Lineage2026-04-25 DeepSeek VL2: Practitioner’s Guide to the MoE Vision-Language Family2026-04-25 DeepSeek VL: The First-Generation Vision-Language Model, Reviewed2026-04-25 DeepSeek Math 7B: Benchmarks, GRPO and How to Use It in 20262026-04-25 DeepSeek Coder V2: The Open-Source MoE Code Model Explained2026-04-25 DeepSeek R1 Distill: The Six Reasoning Models You Can Run Locally2026-04-25 DeepSeek V2 Explained: The MoE Model That Started a Lineage2026-04-25 DeepSeek V4 Preview: Pro and Flash Tiers, 1M Context, Tested2026-04-24 DeepSeek V4-Pro review: the 1.6T open-weight frontier model2026-04-24 DeepSeek V4-Flash: The Cost-Efficient Tier of V4 Explained2026-04-24 DeepSeek R1 explained: benchmarks, pricing, and the V4 migration2026-04-24 DeepSeek V3 Explained: The 671B MoE That Reset Open-Weight Economics2026-04-24 DeepSeek Coder: A Practitioner’s Guide to the Model Family2026-04-24 DeepSeek V3.2 explained: sparse attention, benchmarks and what replaced it2026-04-24