3 verified stories covering MoE architecture, product updates and industry developments.
Moonshot AI released the full production-grade Kimi K2.6 model, which scored 54.0 on HLE-Full, surpassing closed-source models Claude Opus 4.6 and GPT-5.4. The 1-trillion-parameter MoE model activates only 32B parameters per inference and supports up to 300 parallel sub-agents.
NVIDIA has released the Nemotron 3 series, including model weights, a 3 trillion token pre-training dataset, reinforcement learning pipelines, and evaluation tools, all under open licenses.
Mistral released Small 4, a single MoE model that merges three previous standalone models into one deployment, supporting text reasoning, image understanding, code generation, function calling, and JSON output with a 256K context window.