Nemotron 3.5 Lightning
NVIDIA · released Aug 11, 2026
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
Specification
- Context window
- 262K
- Max output
- 236K
- Knowledge cutoff
- Not stated
- Parameters
- 31.6B
- Licence
- other
- Serving providers
- 5
- Moderated
- No
- Uptime
- 100.0%
Intelligence
12.9
52th percentile
Coding
26.8
Coding Index
Agentic
3.5
Agentic Index
Output speed
226 t/s
Median across providers
Latency
194ms
Time to first token
Cost per task
$0.02
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- GPQA Diamond74.3%
- AA-LCR (long context)60.3%
- SciCode32.1%
- Humanity's Last Exam10.6%
- τ²-bench (Telecom)8.9%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 74.3% |
| AA-LCR (long context) | 60.3% |
| SciCode | 32.1% |
| Humanity's Last Exam | 10.6% |
| τ²-bench (Telecom) | 8.9% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Command A+Cohere13.1
- R1DeepSeek13.1
- GPT-5 NanoOpenAI13.0
- Nemotron 3.5 LightningNVIDIA12.9
- 12.9
- GLM 4.5Z.ai12.8
- Kimi K2 0711Moonshot AI12.7
- GPT-4.1OpenAI12.7
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Command A+ | 13.1 |
| R1 | 13.1 |
| GPT-5 Nano | 13.0 |
| Nemotron 3.5 Lightning | 12.9 |
| Nemotron 3.5 Lightning (free) | 12.9 |
| GLM 4.5 | 12.8 |
| Kimi K2 0711 | 12.7 |
| GPT-4.1 | 12.7 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.07
- Output / 1M tokens
- $0.2
- Cached input / 1M
- $0.04
- Blended 3:1
- $0.103
One task, estimated
$0.02
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).