Timeline · newest first
- Nov 1519:55
Meituan Open-Sources LongCat-2.5 Weights: 1.6T-Parameter Agent Model Trained Without Nvidia Chips
a 1.6-trillion-parameter agent model opens its full weights under the MIT license, trained and deployed entirely without Nvidia chips, with a Terminal Bench score of 88.4, close to Claude Opus 5's 89.1.
- Nov 220:03
Meituan Launches LongCat-2.5: 1.6T-Parameter Native Multimodal Model for Long-Horizon Agent Tasks
Meituan's LongCat team released LongCat-2.5 on Nov 2, a native multimodal model for long-horizon agent tasks with 1.6 trillion total parameters and about 48 billion activated per token, trained entirely on domestic compute, with a website trial and API now live.
™