llm-benchmarks
githubdrose.io

Ling-3.0-flash Benchmarks


Measured on novita

12 runs
Avg Tokens / Second
42.45
Avg Time to First Token (ms)
1370.00
Runs Analysed
12
Last Updated
Sep 1, 2026, 03:47 AM

Throughput distribution

Throughput over time

Ling-3.0-flashdeepinfra1tok/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 52 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)
novitaLing-3.0-flash45.1041.0047.001280.00
novitaLing-3.0-flash39.8035.3043.301460.00

Frequently Asked Questions

How fast is Ling-3.0-flash?
The latest rolling average throughput is 42.45 tokens per second with an average time to first token of 1370.00 ms across 12 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, 03:47 AM.

Related models