Skip to main content
Van Data Team
Current modelNVIDIA

Nemotron 3.5 Lightning benchmarks, pricing and specs

Nemotron 3.5 Lightning is a NVIDIA model released on August 11, 2026 that takes text input and produces text. Its price is not published and accepts up to 1,000,000 tokens of context. It scores 1349 Elo on Arena Text, #47 of 49 current models (Arena, measured October 8, 2026).

Context window
1M
Arena Text
1349 Elo · #47/49

Data verified October 13, 2026 · Dataset 2026-10-13

Share this

Key facts

Provider
NVIDIA
Model family
Nemotron 3.5
Release date
August 11, 2026
Status
Current
Access
open weights
API model id
Not reported
Context window
1,000,000 tokens
Max output
Not reported
Input
text
Output
text
Task families
text
Declared capabilities
reasoning, agentic coding

Nemotron 3.5 Lightning pricing

UnitPrice (USD)TierAppliesSource
1M input tokensNot reportedstandardCurrent
1M output tokensNot reportedstandardCurrent
1M input tokensNot reportedcachedCurrent

Independent benchmark results

Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. NVIDIA's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.

BenchmarkScoreRankMeasuredSource
Arena Text1349 Elo#47 of 49October 8, 2026Arena · 2026-10-12

Strengths, cautions and best uses

Strengths

  • A 30B mixture-of-experts model with 3B active parameters; NVIDIA reports up to 4x the output speed of similar-sized models
  • Weights, training data and recipes are released under the OpenMDW-1.1 licence, in BF16 and NVFP4
  • Context of up to 1M tokens, or 256K on a single H100

Cautions

  • On NVIDIA's own table it trails Qwen 3.6 35B A3B on SWE-bench Verified (51.56 against 70.12)
  • NVIDIA sells no per-token API for it; hosted prices come from third parties

Best for

  • Fast, low-cost agent subtasks such as tool calls
  • Self-hosted agents on one GPU

Alternatives to Nemotron 3.5 Lightning

The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.

Compare Nemotron 3.5 Lightning with

Nemotron 3.5 Lightning FAQ

What is the context window of Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning accepts up to 1,000,000 tokens of context. That ranks #25 of 57 current text models by context length.

How does Nemotron 3.5 Lightning score on independent benchmarks?

Nemotron 3.5 Lightning scores 1349 Elo on Arena Text, #47 of 49 current models (Arena, measured October 8, 2026). These are independent evaluations, not NVIDIA's own launch figures.

Is Nemotron 3.5 Lightning open source or API only?

Nemotron 3.5 Lightning is released as open weights that you can run yourself.

What are the best alternatives to Nemotron 3.5 Lightning?

The closest current alternatives by price and measured performance are Grok 4.6 (105 points higher on Arena Text, 1454 vs 1349), Muse Glimmer (76 points higher on Arena Text, 1425 vs 1349), DeepSeek-V4-Pro (116 points higher on Arena Text, 1465 vs 1349) and Gemini 3.7 Flash (137 points higher on Arena Text, 1486 vs 1349).

Sources

Cite this page

Van Data Team. "Nemotron 3.5 Lightning Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-13. https://vandatateam.com/ai-model-benchmarks/nemotron-3-5-lightning

Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.

Production evaluation

Deciding whether Nemotron 3.5 Lightning fits your workload?

Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • Evaluation cases and acceptance thresholds tied to real work
  • Model routing, fallbacks and cost controls
Compare all modelsDiscuss your evaluation