llm-benchmarks
githubdrose.io

inception Provider Benchmarks


Measured over the last 30 days

Models Tracked
3
Avg Tokens / Second
54.63
Avg Time to First Token (ms)
1656.67
Last Updated
Sep 1, 2026

All inception models

3 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Mercury 261.5035.40101.001450.00
Mercury 260.9027.60115.001250.00
Mercury 2.5 Preview41.5041.5041.502270.00

Frequently Asked Questions

Which inception model is fastest?
Based on recent tests, Mercury 2 shows the highest average throughput among tracked inception models.
How many recent measurements feed this dashboard?
This provider summary aggregates 39 individual prompts measured across 39 monitoring runs over the past month.