llm-benchmarks
githubdrose.io

reka Provider Benchmarks


Measured over the last 30 days

Models Tracked
10
Avg Tokens / Second
23.68
Avg Time to First Token (ms)
5221.00
Last Updated
Oct 14, 2026

All reka models

10 live · one row per model · fastest first · 1 folded behind their current lane
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Reka Edge65.2062.9068.10610.00
GLM 5.244.6044.6044.601010.00
Gemma 4 26B A4B24.4024.4024.40850.00
DeepSeek V4 Pro 042323.8019.8029.501450.00
DeepSeek V4 Flash 073120.402.6546.605180.00
DeepSeek V4 Pro 081319.6010.8029.901530.00
Gemma 4 31B19.5011.1027.10920.00
DeepSeek V4 Flash 04239.499.499.495360.00
Qwen3.6 35B A3B6.471.1810.5013300.00
Qwen3.8 27B3.371.645.9922000.00

Frequently Asked Questions

Which reka model is fastest?
Based on recent tests, Reka Edge shows the highest average throughput among tracked reka models.
How many recent measurements feed this dashboard?
This provider summary aggregates 1560 individual prompts measured across 1436 monitoring runs over the past month.