Artificial Analysis lists NVIDIA's Nemotron Nano 9B V2
Artificial Analysis has published a release page for NVIDIA's Nemotron Nano 9B V2, covering two model variants and reporting a 0.79-second time to first answer token for the reasoning version.
Independent benchmarking firm Artificial Analysis has added NVIDIA's Nemotron Nano 9B V2 to its release tracker. The page covers two models under the release, and each has its own intelligence, performance and pricing profile.
The only headline figure on the page is latency. Of the two, NVIDIA Nemotron Nano 9B V2 (Reasoning) has the lower time to first answer token, at 0.79 seconds. The page does not give the second variant's name or latency.
Artificial Analysis compares models only within their own class. Reasoning models are compared with both reasoning and non-reasoning models, while non-reasoning models are compared only with each other. Open-weights models are grouped by size, and the "Small" tier covers 4B to 40B parameters. Proprietary models are grouped by blended price, using a 3:1 input-to-output ratio.
The page also lists the evaluations behind the firm's capability indexes. These include AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf, MLCR-AA, CritPt v2 (Hard Subset), Terminal-Bench 4.0, Terminal-Bench-Science 0.1 and FrontierCode-AA 2.0. Charts on the page cover Intelligence Index scores, cost per task and time per task.
The available text does not include the model's actual index scores, its prices, its output speed or its licensing terms. It also does not say how it ranks against peers.