Private AI
Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant. Included in the NanoGPT subscription.
Added Aug 12, 2026
Model weightsContext Window
1.0M
Max Output
65.5K
Input Price (Auto)
$0.053/1M
Output Price (Auto)
$0.21/1M
Cache Read (Auto)
$0.011/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
23.6
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Coding Index
26.8
Agentic Index
13.8
GPQA Diamond
Graduate-level scientific reasoning
74.3%
Better than 58% of models compared
HLE
Humanity's Last Exam
10.6%
Better than 59% of models compared
AA-LCR
Long context reasoning evaluation
55.3%
Better than 58% of models compared
GDPval-AA
Economically valuable tasks
16.2%
CritPt
Research-level physics reasoning
0.0%
SciCode
Python programming for scientific computing
31.6%
Better than 45% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
14.4%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
37.6%
Last updated Aug 13, 2026
Artificial Analysis