Meituan · Code Generation
LongCat-2.0
Open-source 1.6T-parameter MoE agentic coding model (~48B active/token via zero-computation experts) with native 1M-token context and LongCat Sparse Attention; scores 59.5 SWE-bench Pro and 70.8 Terminal-Bench, trained entirely on a 50,000-card domestic Chinese compute cluster (no A100/H100).
Open the source ↗Similar Language Models releases
- Clover-35B-A3B-Preview
DiffuSpace · Diffusion MoE LLM · Week 45, 2026
- Groot-280B-A16B-261023
GrootTeam · Open reasoning MoE · Week 45, 2026
- Apex-35B-V1.0
Apex Intelligence · Research automation LLM · Week 45, 2026
- Kimi K3.1 Pro
Moonshot AI · Open-Weight Frontier · Week 44, 2026
- DeepSeek-V4.1-Flash-1017
DeepSeek · Open-Weight LLM · Week 44, 2026
- Step 5 Preview
StepFun · Open Weight Release · Week 43, 2026
More from Meituan
- LongCat-Video-Avatar-1.5
Meituan · Text-to-Video · Week 21, 2026
- LongCat-AudioDiT
Meituan · Text-to-Speech · Week 14, 2026
- LongCat-Video-Avatar
Meituan · Text-to-Video · Week 51, 2025
- LongCat-Image
Meituan · Text-to-Image · Week 50, 2025
- LongCat-Video
Meituan · Text-to-Video · Week 44, 2025
- LongCat-Flash-Chat
Meituan · Text Generation · Week 32, 2025
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.