llm-benchmarks
githubdrose.io

claude-on-aws Provider Benchmarks


Measured over the last 30 days

Models Tracked
8
Avg Tokens / Second
17.78
Avg Time to First Token (ms)
2970.00
Last Updated
Sep 2, 2026

All claude-on-aws models

8 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Claude Sonnet 4.623.3021.6025.901460.00
Claude Opus 4.821.2019.6023.401760.00
Claude Sonnet 4.521.1017.7023.901440.00
Claude Opus 4.721.0017.2025.301380.00
Claude Opus 4.519.8016.1021.902180.00
Claude Sonnet 518.7015.2021.402190.00
Claude Opus 4.617.0014.2020.802670.00
Claude Fable 53.292.044.076930.00

Frequently Asked Questions

Which claude-on-aws model is fastest?
Based on recent tests, Claude Sonnet 4.6 shows the highest average throughput among tracked claude-on-aws models.
How many recent measurements feed this dashboard?
This provider summary aggregates 7755 individual prompts measured across 3999 monitoring runs over the past month.