llm-benchmarks
githubdrose.io

poolside Provider Benchmarks


Measured over the last 30 days

Models Tracked
2
Avg Tokens / Second
29.70
Avg Time to First Token (ms)
2765.00
Last Updated
Oct 6, 2026

All poolside models

2 live · one row per model · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Laguna S 2.139.4011.5067.302690.00
Laguna XS 2.120.0019.6020.502840.00

Frequently Asked Questions

Which poolside model is fastest?
Based on recent tests, Laguna S 2.1 shows the highest average throughput among tracked poolside models.
How many recent measurements feed this dashboard?
This provider summary aggregates 4 individual prompts measured across 4 monitoring runs over the past month.