// head_to_head
Nemotron 3.5 Super VL vs Nemotron 3 Super
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
Nemotron 3.5 Super VL is the cheaper of the two; neither can be ranked on quality here.
Nemotron 3 Super does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
nvidia
Nemotron 3.5 Super VL
- Blended / 1M
- $0.237
- Context
- 1.0M
- Released
- Oct 15, 2026
- Overall score
- 50.2
nvidia
Nemotron 3 Super
- Blended / 1M
- $0.825
- Context
- 1.0M
- Released
- Mar 11, 2026
- Overall score
- Not evaluated
Specs and pricing
| Metric | Nemotron 3.5 Super VL | Nemotron 3 Super |
|---|---|---|
| LiveBench overall Weighted mean of the seven LiveBench category scores, 0–100. Higher is better. | 50.2 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0030 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $0.237win | $0.825 |
| Input price / 1M | $0.150win | $0.300 |
| Output price / 1M | $0.500win | $2.40 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.020win | $0.150 |
| Context window | 1.0M | 1.0M |
| Max output tokens | 236K | 262K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Nemotron 3.5 Super VL on top, Nemotron 3 Super below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | Nemotron 3.5 Super VL | Nemotron 3 Super |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $66.64/mo | $253.20/mo |
| RAG assistant 8K in / 600 out × 100K requests | $98.00/mo | $324.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $87.20/mo | $348.00/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $181.00/mo | $472.50/mo |
| Bulk classification 500 in / 20 out × 5M requests | $360.00/mo | $915.00/mo |
Which should you pick?
You are cost-constrained
Nemotron 3.5 Super VL
Cheaper on blended list price at $0.237 per million tokens.
Nemotron 3.5 Super VL vs Nemotron 3 Super FAQ
Which is better, Nemotron 3.5 Super VL or Nemotron 3 Super?
Nemotron 3.5 Super VL is the cheaper of the two; neither can be ranked on quality here. Nemotron 3 Super does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Is Nemotron 3.5 Super VL cheaper than Nemotron 3 Super?
Nemotron 3.5 Super VL is cheaper. On a 3:1 input:output blend, Nemotron 3.5 Super VL lists at $0.237 per million tokens and Nemotron 3 Super at $0.825 — Nemotron 3.5 Super VL is 3.5× cheaper. Input and output are priced separately — Nemotron 3.5 Super VL charges $0.150 in and $0.500 out, Nemotron 3 Super charges $0.300 and $2.40 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Does Nemotron 3.5 Super VL or Nemotron 3 Super have a bigger context window?
They are effectively the same — 1.0M for Nemotron 3.5 Super VL and 1.0M for Nemotron 3 Super.
Do Nemotron 3.5 Super VL and Nemotron 3 Super support prompt caching?
Both publish a cached-input rate: $0.020 per million for Nemotron 3.5 Super VL and $0.150 for Nemotron 3 Super, against full input rates of $0.150 and $0.300. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-10-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.