llm-benchmarks
githubdrose.io

relace Provider Benchmarks


Measured over the last 30 days

Models Tracked
8
Avg Tokens / Second
27.22
Avg Time to First Token (ms)
16326.25
Last Updated
Oct 17, 2026

All relace models

8 live · one row per model · fastest first · 4 folded behind their current lane
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Relace Search92.6092.6092.60480.00
GLM 5.335.3028.7046.401280.00
GLM 5.229.8018.4052.001340.00
DeepSeek V4 Flash 073121.203.5359.505930.00
MiMo-V2.6-Flash18.3016.3020.302380.00
DeepSeek V4 Pro 042317.6010.6028.303300.00
DeepSeek V4.1 Flash1.890.634.2143600.00
DeepSeek Flash Latest1.070.601.5472300.00

Frequently Asked Questions

Which relace model is fastest?
Based on recent tests, Relace Search shows the highest average throughput among tracked relace models.
How many recent measurements feed this dashboard?
This provider summary aggregates 963 individual prompts measured across 921 monitoring runs over the past month.