MMODELYST
Models/NVIDIA Nemotron 3 Nano 30B A3B
MDL

NVIDIA Nemotron 3 Nano 30B A3B

NVIDIA

Verified against Artificial Analysis · Jul 13, 2026
Capability
72
percentile index
Price /M
$0.05 / $0.2
in / out
Context
Avg score
51.9
10 benchmarks
AA Intelligence
14.2
index
Speed
147 tok/s
TTFT 0.8s
Released
Dec 15, 2025
About

NVIDIA Nemotron 3 Nano 30B A3B is a open-weights model in the NVIDIA family from NVIDIA. Benchmarked on 10 evals, averaging 51.9.

Benchmark scores · 10
avg 51.9 — higher is better
AIME
91
MMLU-Pro
79.4
GPQA Diamond
75.7
LiveCodeBench
74.1
IFBench
71.1
τ²-bench
40.9
AA Long-Context Reasoning
33.7
SciCode
29.6
Terminal-Bench Hard
13.6
Humanity's Last Exam
10.2
Details
PublisherNVIDIA
FamilyNVIDIA
Parameters
License
WeightsOpen
ReleasedDec 15, 2025
Performance & price
Output speed147 tok/s
Latency (TTFT)0.8s
First answer14s
Price in / out$0.05 / $0.2 per 1M
Blended price$0.088 / 1M
Coding index14.4
Math index91.0

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0.2/M