Poolside: Laguna M.1

Poolside's Laguna M.1, a flagship coding agent model, demonstrates exceptional performance across several key metrics. It consistently ranks among the fastest models and offers highly competitive pricing, achieving an "Infinityth percentile" in both speed and price across 8 benchmarks. The model also exhibits outstanding reliability with a 99% success rate, indicating minimal technical failures. In terms of benchmark performance, Laguna M.1 excels in General Knowledge, achieving perfect 100% accuracy and being noted as the most accurate model at its price point and among models of comparable speed. It also shows strong capabilities in Reasoning (98% accuracy, 90th percentile) and Email Classification (98% accuracy, 60th percentile). Its Coding performance is solid at 91% accuracy (66th percentile), and Mathematics at 91% (55th percentile). A notable weakness is its Instruction Following, where it scored 0% accuracy, suggesting significant limitations in processing complex, multi-layered instructions. Hallucinations are present at 84% accuracy, indicating room for improvement in acknowledging uncertainty.