Ling-3.1
❖ We’re introducing Ling-3.1-flash, an upgraded native hybrid reasoning model designed for complex, real-world tasks. With 560B total parameters, 25B active parameters per token, and a 1M-token context window, Ling-3.1-flash builds upon Ling-3.0-flash with improvements in architecture and performance on real-world tasks.
MiMo-V2.6
❖ MiMo-V2.6-Pro-RL is the flagship checkpoint of the MiMo-V2.6 series. The series is built to scale reinforcement learning toward self-improvement — scaling RL compute, environment diversity, and grader compute together, so the model keeps expanding its capability frontier through exploration and feedback.
Step-5
❖ Step-5-Preview is our flagship foundation model for real-world agentic work — a 600B-parameter sparse Mixture-of-Experts model with 27B active parameters, a 1M-token context window, and native support for text, image, and video inputs. It targets professional domains such as AI coding, software engineering, professional knowledge work, and financial analysis.
LongCat DeepResearch
❖ LongCat DeepResearch organizes open-ended research around an executable ResearchSpec. Multiple planners explore sources and refine a shared agenda; independent Researchers develop citation-bearing sections; direct assembly and coordinated editing turn those sections into a complete report without asking one final writer to regenerate everything.
DeepSeek-V4.1
❖ We present DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4.1-Flash with 552B parameters (8B / 16B activated) and DeepSeek-V4-Pro with 1.6T parameters (49B activated) — both supporting a context length of one million tokens.
K2 Horizon
❖ K2-Horizon-375B-A23B is the flagship of the K2 Horizon family: a sparse Mixture-of-Experts model that has 375B total parameters and activates 23B per token, with a 512K context window. We have released the checkpoints, data, and training code. With full visibility into training and evaluation, strong agentic capabilities, and a low cost per task, K2 Horizon gives researchers and builders a dependable foundation for long-context applications at every scale.
Hy4
❖ Hy4 preview is a new-generation Mixture-of-Experts (MoE) flagship model developed by the Tencent Hy Team. The model comprises 770B total parameters, of which 49B are activated per token. We scaled Hy4 on three fronts: model size, context length, and training data.
GLM-5.3
❖ GLM-5.3 is our latest flagship model for coding and long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and delivers that capability on a solid 1M-token context. It is pure open with an MIT open-source license — no regional limits, technical access without borders.