Poolside drops Laguna S 2.1, an open-weight coding model that beats rivals 10x its size

Poolside released Laguna S 2.1, an open-weight coding model, on Tuesday. The San Francisco AI lab announced the model as its most capable to date. Laguna S 2.1 is a 118-billion-parameter Mixture-of-Experts system that activates only 8 billion parameters per token and supports a context window of up to 1 million tokens. According to benchmarks published by the company, it matches or beats open models several times its size on agentic coding tasks. The weights are available immediately on Hugging Face under the permissive OpenMDW-1.1 license. Poolside reports that Laguna S 2.1 scores 70.2% on Terminal-Bench 2.1, placing it ahead of DeepSeek-V4-Pro-Max, Thinking Machines' Inkling, and Nvidia's Nemotron 3 Ultra. On SWE-Bench Multilingual, it posts 78.5%, and on SWE-Bench Pro's public dataset, 59.4%. The model went from the start of pre-training on May 22 to public launch in under nine weeks, trained on 4,096 Nvidia H200 GPUs.