Back

NVIDIA

Nemotron 3 Nano Omni 30B A3B Reasoning

ReasoningOpen weightsModels.devHugging Face
Intelligence
10.3
Rank 420 of 744 measured models
Coding
13.8
Rank 254 of 298 measured models
Output speed
237 t/s
Rank 22 of 403 measured models
Price/1M
$0.45
Rank 256 of 659 measured models
Context window
256K
Rank 518 of 1199 measured models

Nemotron 3 Nano Omni 30B A3B Reasoning scores 10.3 on the Artificial Analysis Intelligence Index, ranking 420th of 744 measured models. The closest models on this index are Gemini 2.5 Flash-Lite (10.4), GPT-5 (ChatGPT) (10.4), and Grok 3 Reasoning Beta (10.4). At $0.45 per million tokens (3:1 input/output blended price), it is more expensive than Gemini 2.5 Flash-Lite ($0.175). With an output speed of 237 t/s, it is slower than Gemini 2.5 Flash-Lite (287 t/s).

Artificial Analysis Indices
Intelligence10.3
Rank 420 of 744 measured models
Coding13.8
Rank 254 of 298 measured models
Standard Benchmarks
GPQA Diamond46.9%
Rank 491 of 619 measured models
HLE4.8%
Rank 496 of 664 measured models
IFBench63.2%
Rank 116 of 450 measured models
AA-LCR39.7%
Rank 372 of 575 measured models
TerminalBench Hard8.3%
Rank 249 of 432 measured models
Terminal-Bench 2.16.7%
Rank 207 of 244 measured models
τ²-Bench45.3%
Rank 224 of 440 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