llm-benchmarks
githubdrose.io

nova-lite Benchmarks


Measured on bedrock

1353 runs
Avg Tokens / Second
91.00
Avg Time to First Token (ms)
380.00
Runs Analysed
1353
Last Updated
Aug 14, 2026, 02:16 AM

Throughput distribution

Throughput over time

nova-litebedrock89tok/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 129 tok/s (99th percentile) · dashed rule is the model's own mean · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
bedrocknova-lite91.001.05132.00380.00

Frequently Asked Questions

How fast is nova-lite?
The latest rolling average throughput is 91.00 tokens per second with an average time to first token of 380.00 ms across 1353 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 14, 2026, 02:16 AM.

Related models