llm-benchmarks
githubdrose.io

KAT-Coder-Pro V2 Benchmarks


Measured on streamlake

42 runs
Avg Tokens / Second
37.50
Avg Time to First Token (ms)
1200.00
Runs Analysed
42
Last Updated
Aug 18, 2026, 05:59 PM

Throughput distribution

Throughput over time

KAT-Coder-Pro V2atlas-cloud1tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 33 tok/s (99th percentile) · dashed rule is the model's own mean · 3 further providers not drawn · 1 samples above the ceiling drawn at it

Every provider serving this model

2 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
streamlakeKAT-Coder-Pro V237.4029.6042.101220.00
streamlakeKAT-Coder-Pro V237.6027.5051.801180.00

Frequently Asked Questions

How fast is KAT-Coder-Pro V2?
The latest rolling average throughput is 37.50 tokens per second with an average time to first token of 1200.00 ms across 42 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 18, 2026, 05:59 PM.

Related models