llm-benchmarks
githubdrose.io

chutes Provider Benchmarks


Measured over the last 30 days

Models Tracked
7
Avg Tokens / Second
13.85
Avg Time to First Token (ms)
19021.00
Last Updated
Sep 1, 2026

All chutes models

7 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Gemma 4 31B9.647.4311.803030.00
Kimi K2.63.342.094.3019500.00
Kimi K2.62.670.945.1026900.00
Qwen3.8 27B2.491.174.6533700.00
Qwen3.8 27B1.371.371.3741200.00
GLM 5.10.970.970.9765000.00
GLM 5.10.950.721.2167600.00

Frequently Asked Questions

Which chutes model is fastest?
Based on recent tests, Gemma 4 31B shows the highest average throughput among tracked chutes models.
How many recent measurements feed this dashboard?
This provider summary aggregates 2493 individual prompts measured across 2415 monitoring runs over the past month.