llm-benchmarks
githubdrose.io

reka Provider Benchmarks


Measured over the last 30 days

Models Tracked
11
Avg Tokens / Second
24.47
Avg Time to First Token (ms)
4750.00
Last Updated
Oct 17, 2026

All reka models

11 live · one row per model · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Reka Edge66.3064.5068.10590.00
GLM 5.244.6044.6044.601010.00
Qwen3.5-27B29.5029.5029.50710.00
Gemma 4 26B A4B24.4024.4024.40850.00
DeepSeek V4 Pro 042323.8019.8029.501450.00
DeepSeek V4 Flash 073122.102.6546.604530.00
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 1570 individual prompts measured across 1465 monitoring runs over the past month.