llm-benchmarks
githubdrose.io

io-net Provider Benchmarks


Measured over the last 30 days

Models Tracked
3
Avg Tokens / Second
9.31
Avg Time to First Token (ms)
17046.83
Last Updated
Sep 1, 2026

All io-net models

3 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Mistral Nemo27.9010.9037.00890.00
Qwen3.6 35B A3B7.036.207.988730.00
DeepSeek V4 Flash 07311.840.863.8050100.00

Frequently Asked Questions

Which io-net model is fastest?
Based on recent tests, Mistral Nemo shows the highest average throughput among tracked io-net models.
How many recent measurements feed this dashboard?
This provider summary aggregates 398 individual prompts measured across 352 monitoring runs over the past month.