llm-benchmarks
githubdrose.io

sambanova Provider Benchmarks


Measured over the last 30 days

Models Tracked
7
Avg Tokens / Second
24.14
Avg Time to First Token (ms)
4533.09
Last Updated
Sep 1, 2026

All sambanova models

7 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
gpt-oss-120b54.7013.3083.002490.00
DeepSeek V3.149.7045.6056.20980.00
MiniMax M339.7039.7039.701570.00
Gemma 4 31B39.2036.5041.401550.00
MiniMax M2.731.2023.4042.502350.00
DeepSeek V3.226.109.4340.103570.00
MiniMax M2.724.4022.6028.003010.00

Frequently Asked Questions

Which sambanova model is fastest?
Based on recent tests, gpt-oss-120b shows the highest average throughput among tracked sambanova models.
How many recent measurements feed this dashboard?
This provider summary aggregates 814 individual prompts measured across 726 monitoring runs over the past month.