llm-benchmarks
githubdrose.io

modelrun Provider Benchmarks


Measured over the last 30 days

Models Tracked
5
Avg Tokens / Second
22.88
Avg Time to First Token (ms)
5104.41
Last Updated
Sep 1, 2026

All modelrun models

5 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Gemma 4 31B96.8061.50132.00300.00
Gemma 4 31B75.7057.1095.20530.00
Kimi K2.7 Code26.6017.0036.102310.00
MiniMax M321.6014.8031.003220.00
Auto Router (Beta)8.997.7610.207420.00

Frequently Asked Questions

Which modelrun model is fastest?
Based on recent tests, Gemma 4 31B shows the highest average throughput among tracked modelrun models.
How many recent measurements feed this dashboard?
This provider summary aggregates 375 individual prompts measured across 334 monitoring runs over the past month.