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 Sp
Why CEREBRO kept it
LongCat-2.0: 1.6T MoE, 1M context, built for agentic coding, outperforms GPT-5.5 SWE-bench
The text below is an automated extraction of the article at https://x.com/Meituan_LongCat/status/2071783587205308721, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (x.com).
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 Sp
> LongCat-2.0: 1.6T MoE, 1M context, built for agentic coding, outperforms GPT-5.5 SWE-bench
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 · BrowseCo
Backlinks
Appeared in 1 briefing