poolside

Comparing 2 models from poolside.

Model Total ▼ Released Context CoTTooling Creative Writing Language Utility Reasoning Text Editing Rule Following Hallucination
Laguna S 2.179.98%Jul 2, 261m98.78%74.16%97.91%81.67%69.59%91.27%33.30%93.17%
Laguna XS 2.175.42%Jul 2, 26262k88.97%77.28%64.47%78.98%67.05%87.94%46.56%92.09%
Model Performance
Cost vs Performance

Compares total benchmark cost against overall score for poolside models. Quadrant lines are drawn at the median values.

Cost Breakdown

Total benchmark cost per model, broken down by input, reasoning, and output tokens. Toggle between USD and token views.