AI 精选动态
智能评分 69
美团发布LongCat-2.0
AI 推荐理由
该模型采用LongCat Sparse Attention和Zero-Compute Experts等创新架构，且在多个编码基准上超越GPT-5.5，值得深入研究其技术细节与部署方案。核心解读
美团发布LongCat-2.0，1.6T参数MoE模型，约48B激活参数，支持1M上下文窗口，基于AI ASIC超算集群训练与部署。在SWE-bench Pro上得分59.5，超过GPT-5.5的58.6，并在Terminal-Bench、FORTE等多项基准中取得领先成绩。
全文
Meituan released LongCat-2.0, a new 1.6T parameter model with 1M context window!
> Both the full training run and the large-scale deployment are built entirely on AI ASIC superpods.
It is also available for testing on OpenRouter under the Owl Alpha name. https://t.co/SoYYETUkY0
> **引用原帖 Meituan LongCat (@Meituan_LongCat):**
> Introducing LongCat-2.0 🐱
> 1.6T parameters · MoE with ~48B active · 1M context
> The full model behind Owl Alpha on @OpenRouter — now available.
> Built for agentic coding from the ground up:
> ◆ LongCat Sparse Attention (LSA) — scales efficiently for 1M-context tokens
> ◆ Zero-Compute Experts — dynamic activation 33B–56B per token, zero wasted compute
> ◆ MOPD — three specialized expert groups (Agent / Reasoning / Interaction), gate-routed per task
> How it stacks up:
> → Terminal-Bench 2.1: 70.8
> → SWE-bench Pro: 59.5 (GPT-5.5: 58.6)
> → SWE-bench Multilingual: 77.3
> → FORTE: 73.2 · RWSearch: 78.8 · BrowseComp: 79.9
> 📖 Tech Blog: https://t.co/4KrjyKiDBn
> Try it across different scenarios 🧵👇
> https://x.com/Meituan_LongCat/status/2071783587205308721