// head_to_head
Nemotron 3.5 Super VL vs Inkling 2 Small
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.
Inkling 2 Small 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
- $0.230
- Context
- 1.0M
- Released
- Oct 15, 2026
- Overall score
- 47.0
thinkingmachines
Inkling 2 Small
- Blended / 1M
- $0.475
- Context
- 1.0M
- Released
- Nov 9, 2026
- Overall score
- Not evaluated
Specs and pricing
| Metric | Nemotron 3.5 Super VL | Inkling 2 Small |
|---|---|---|
| LiveBench overall Weighted mean of the seven LiveBench category scores, 0–100. Higher is better. | 47.0 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0031 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $0.230win | $0.475 |
| Input price / 1M | $0.150win | $0.300 |
| Output price / 1M | $0.470win | $1.00 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.020win | $0.030 |
| Context window | 1.0M | 1.0M |
| Max output tokens | 944K | 944K |
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, Inkling 2 Small 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 | Inkling 2 Small |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $64.24/mo | $132.56/mo |
| RAG assistant 8K in / 600 out × 100K requests | $96.20/mo | $192.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $84.80/mo | $168.80/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $178.75/mo | $361.50/mo |
| Bulk classification 500 in / 20 out × 5M requests | $357.00/mo | $715.00/mo |
Which should you pick?
You are cost-constrained
Nemotron 3.5 Super VL
Cheaper on blended list price at $0.230 per million tokens.
Nemotron 3.5 Super VL vs Inkling 2 Small FAQ
Which is better, Nemotron 3.5 Super VL or Inkling 2 Small?
Nemotron 3.5 Super VL is the cheaper of the two; neither can be ranked on quality here. Inkling 2 Small 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 Inkling 2 Small?
Nemotron 3.5 Super VL is cheaper. On a 3:1 input:output blend, Nemotron 3.5 Super VL lists at $0.230 per million tokens and Inkling 2 Small at $0.475 — Nemotron 3.5 Super VL is 2.1× cheaper. Input and output are priced separately — Nemotron 3.5 Super VL charges $0.150 in and $0.470 out, Inkling 2 Small charges $0.300 and $1.00 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Does Nemotron 3.5 Super VL or Inkling 2 Small have a bigger context window?
They are effectively the same — 1.0M for Nemotron 3.5 Super VL and 1.0M for Inkling 2 Small.
Do Nemotron 3.5 Super VL and Inkling 2 Small support prompt caching?
Both publish a cached-input rate: $0.020 per million for Nemotron 3.5 Super VL and $0.030 for Inkling 2 Small, 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 2026-11-06, 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.