llm-benchmarks
githubdrose.io

Nemotron 3.5 Super VL Benchmarks


Measured on primeintellect

8 runs
Avg Tokens / Second
31.50
Decode Tokens / Second
—
Avg Time to First Token (ms)
2890.00
Runs Analysed
8
Last Updated
Nov 15, 2026, 04:08 AM

Throughput distribution

Throughput over time

Nemotron 3.5 Super VLprimeintellect168tok/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 · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 296 tok/s (99th percentile) · dashed rule is the model's own mean

Every lane measuring this model

2 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
primeintellectvia OpenRouter31.509.7375.502890.008
primeintellectdirect64.7013.90106.001470.005

Frequently Asked Questions

How fast is Nemotron 3.5 Super VL?
The latest rolling average throughput is 31.50 tokens per second with an average time to first token of 2890.00 ms across 8 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 15, 2026, 04:08 AM.

Related models