Agents / Skills
Laguna S 2.1
A powerful 118B agentic coding model with reasoning and a 1M-token context window.
byPoolside
Playable
Laguna S 2.1 media is blocked
Allow external media to connect to the provider and play this content.
Description
Laguna S 2.1 is a Mixture-of-Experts (MoE) model optimized for long-horizon engineering tasks, featuring a 1M-token context window and a native 'thinking' mode. It is demonstrated performing complex autonomous work including building a rendering engine from an empty folder, optimizing its own agent harness for speed, and re-deriving 50-year-old mathematical proofs.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.