**Cognition's SWE-2 achieves 92.8 on Terminal-Bench 2.1** > SWE-2: 2800B params

**Cognition's SWE-2 achieves 92.8 on Terminal-Bench 2.1**

> SWE-2: 2800B params, k context. See memory requirements, quantization options, and cloud pricing. Models / SWE-2 SWE-2 MoE premier Cognition → Find for my hardware 2.8T total params, 104B active per token (MoE) - the Kimi K3 base with Cognition’s post-training on top, and the first time Cognition has scaled RL into the multi-trillion-parameter regime. The base had already been RL-heavy for agentic coding; Cognition’s...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-11 00:52（北京时间）
- **原文**：[打开原文](https://tokenstead.ai/models/swe-2)