Poolside's Laguna S 2.1 Shows Open-Weight Coding Models Are Closing the Gap
Poolside released Laguna S 2.1, a 118B open-weight mixture-of-experts model with a 1M-token context window that is punching above its class on SWE-Bench Multilingual.
Poolside has released Laguna S 2.1, an open-weight agentic coding model that the company says is outperforming its size class on SWE-Bench Multilingual, according to @wesjh_. The specifications, detailed by @aidailyprimer, describe a 118B-parameter mixture-of-experts architecture with a 1-million-token context window.
Unlock the full briefing
Get every story in today's briefing, the full archive, and the daily AI intelligence brief.
All stories today
Full archive
Daily brief
Cancel anytime. Payments powered by Stripe.