Agents / Skills
Laguna S 2.1
A 118B parameter MoE coding model with long-horizon reasoning and 1M context.
byPoolside
Playable
Description
A Mixture-of-Experts (MoE) model optimized for agentic coding and long-horizon tasks, supporting a context window of up to 1M tokens. It features a dedicated 'thinking mode' that significantly boosts performance on complex software engineering benchmarks like DeepSWE and Terminal-Bench.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.