llm-benchmarks
githubdrose.io

KAT-Coder-Pro V2.5 Benchmarks


Measured on streamlake

5 runs
Avg Tokens / Second
7.94
Avg Time to First Token (ms)
9025.00
Runs Analysed
5
Last Updated
Sep 1, 2026, 02:54 AM

Throughput distribution

Throughput over time

KAT-Coder-Pro V2.5atlascloud0tok/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 1 tok/s (99th percentile) · dashed rule is the model's own mean · 2 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 V2.510.806.4513.406150.00
streamlakeKAT-Coder-Pro V2.55.075.075.0711900.00

Frequently Asked Questions

How fast is KAT-Coder-Pro V2.5?
The latest rolling average throughput is 7.94 tokens per second with an average time to first token of 9025.00 ms across 5 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 02:54 AM.

Related models