Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with Native 1M Context and LongCat Sparse Attention

Meituan has released LongCat-2.0 , a large-scale Mixture-of-Experts (MoE) language model. It carries 1.6 trillion total parameters and activates about 48 billion per token . The model targets agentic coding: code understanding, generation, and execution inside agent workflows.

Two facts stand out. First, LongCat-2.0 supports a native 1-million-token context window . Second, both training and serving ran entirely on domestic AI ASIC superpods .

LongCat-2.0 is Meituan’s next-generation trillion-parameter open model. It follows LongCat-Flash, a 560B model released in 2025. The architecture was designed around one goal: reliable, efficient agentic coding.

Pretraining spanned more than 35 trillion tokens over millions of accelerator-hours. Meituan reports no rollbacks or irrecoverable loss spikes during the run. That stability claim matters on non-Nvidia hardware, where tooling is less mature.

The design combines four ideas that reduce the cost of scale. Each one is worth understanding on its own.

For serving, Meituan uses a 6D parallelism scheme and a prefill-decode disaggregated architecture. It also employs ‘super kernels’ and L2-cache weight prefetching to hide I/O latency.

Meituan positions LongCat-2.0 as an agentic coding model. Every figure below comes from Meituan’s own testing.

On SWE-bench Pro, Meituan reports LongCat-2.0 edging GPT-5.5 (58.6). Meituan also claims overall performance comparable to Google’s Gemini 3.1 Pro. The reported edge is concentrated in software engineering. On broader general-agent benchmarks such as FORTE and BrowseComp, coverage indicates it trails leading frontier systems. Independent leaderboard confirmation is not yet available.

The jump from the previous generation is large on paper. This table uses each model’s published specifications.

LongCat-2.0 is tuned for agent-style software work, not casual chat. A few concrete patterns fit its strengths.

These patterns run inside standard agent harnesses. Dev teams can therefore adopt the model without building new tooling.

LongCat-2.0 is reachable through the LongCat API Platform. It exposes both OpenAI-compatible and Anthropic-compatible endpoints. The model is also on OpenRouter and in harnesses like Claude Code, OpenClaw, OpenCode, and Codex. Local self-hosting is not yet possible, since weights remain pending.