AI 精选动态
智能评分 65
Meituan 发布 LongCat-2.0 模型
AI 推荐理由
与 GPT-5.5 在 SWE-bench Pro 上对比并超越，值得关注其稀疏注意力与零计算专家等技术创新。核心解读
美团（Meituan）发布 LongCat-2.0 模型，1.6T 参数，MoE 架构约 48B 活跃参数，支持 1M 上下文。采用 LongCat Sparse Attention、Zero-Compute Experts 和 MOPD 分组，在 Terminal-Bench 2.1 上得分 70.8，SWE-bench Pro 得分 59.5（超越 GPT-5.5 的 58.6），SWE-bench Multilingual 得分 77.3，FORTE 73.2 等。模型专为 agentic coding 构建，并已在 OpenRouter 上线。
全文
When we were in China, @xeophon and I made a quick detour to visit Meituan. They continue to be one of our favorite open model builders, as they're showing how a variety of companies can succeed here and baffle a lot of people as to why they're making models.
Meituan is one of the larger tech companies in China. They're building LLMs to add services to their own products. In China the notion of the "super app" is very popular, so this dream of more services for users with AI is very natural there.
With this, Meituan wants to own the full stack of how they deliver value to their users. When we visited, they were very unassuming about everything. We just met a few people from the LLM team, a quick meeting about building models.
They build general foundational reasoning models, and then fine-tune it further for their products. They can release the general model to support the ecosystem and learn how it can be used.
Their focus was very clearly on ownership, and a hint of cost-saving, so the recent news of v2 being trained on asics fits with that mentality. They want to deliver real products to users with low cost.
Companies like this will keep building models in China. It's a small micro study of how different the players in the AI ecosystem are. Kimi, Z ai, etc are all much flashier offices, come across as the "hot new thing" but Meituan has the talent and resources to build models as well.
Congrats to the Meituan team & thx for having us!
> **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