Back

NVIDIA

NVIDIA Nemotron 3 Nano 30B A3B

ReasoningOpen weights
Intelligence
8.9
Rank 470 of 744 measured models
Coding
14.4
Rank 249 of 298 measured models
Output speed
233 t/s
Rank 25 of 403 measured models
Price/1M
$0.088
Rank 78 of 659 measured models
Context window
1M
Rank 84 of 1199 measured models
Cost per task
$0.0168
Rank 19 of 193 measured models

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) scores 8.9 on the Artificial Analysis Intelligence Index, ranking 470th of 744 measured models. The closest models on this index are Devstral Medium (9.0), Claude 3.5 Haiku (8.9), and Gemini 2.0 Flash (Feb '25) (8.9).

Artificial Analysis Indices
Reasoning
Intelligence8.9
Rank 470 of 744 measured models
Coding14.4
Rank 249 of 298 measured models
Math91.0
Rank 21 of 270 measured models
Agentic1.0
Rank 158 of 189 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Price / 1M tokens
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting9.2
Rank 190 of 218 measured models
Strategy & Ops5.9
Rank 191 of 218 measured models
Legal10.1
Rank 195 of 218 measured models
Engineering12.7
Rank 192 of 217 measured models
Economics14.9
Rank 199 of 225 measured models
Standard Benchmarks
MMLU Pro79.4%
Rank 125 of 349 measured models
GPQA Diamond75.7%
Rank 262 of 619 measured models
HLE11.4%
Rank 303 of 664 measured models
LiveCodeBench74.1%
Rank 50 of 343 measured models
SciCode30.6%
Rank 210 of 231 measured models
AIME 202591.0%
Rank 21 of 270 measured models
IFBench71.1%
Rank 62 of 450 measured models
AA-LCR38.0%
Rank 378 of 575 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy