llm-benchmarks
githubdrose.io

ambient Provider Benchmarks


Measured over the last 30 days

Models Tracked
3
Avg Tokens / Second
15.06
Avg Time to First Token (ms)
10732.65
Last Updated
Sep 1, 2026

All ambient models

3 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
GLM 5.246.7042.5051.50960.00
Kimi K2.7 Code9.136.0612.807180.00
DeepSeek V4 Flash 07312.981.205.6028200.00

Frequently Asked Questions

Which ambient model is fastest?
Based on recent tests, GLM 5.2 shows the highest average throughput among tracked ambient models.
How many recent measurements feed this dashboard?
This provider summary aggregates 632 individual prompts measured across 549 monitoring runs over the past month.