llm-benchmarks
githubdrose.io

sail-research Provider Benchmarks


Measured over the last 30 days

Models Tracked
5
Avg Tokens / Second
12.70
Avg Time to First Token (ms)
12988.59
Last Updated
Sep 1, 2026

All sail-research models

5 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
DeepSeek V4 Pro 081349.5041.5057.50860.00
DeepSeek V4 Flash 042331.1023.2040.40870.00
GLM 5.214.903.1724.107410.00
Kimi K2.63.732.675.4317100.00
DeepSeek V4 Flash 07312.891.584.0920400.00

Frequently Asked Questions

Which sail-research model is fastest?
Based on recent tests, DeepSeek V4 Pro 0813 shows the highest average throughput among tracked sail-research models.
How many recent measurements feed this dashboard?
This provider summary aggregates 942 individual prompts measured across 762 monitoring runs over the past month.