NVIDIAProvisional

Nemotron 3 Nano

Nemotron 3 / Nano · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8

Efficient NVIDIA open model for long-context local or hosted agent workflows.

Objective score

6.9

Confidence

79%

Price evidence

Pricing evidence pending

Support this model Compare trend Official source

Scenario evidence

Six task-specific rankings

Feature development#74Obj. 6.90 · 0%Debug and repair#72Obj. 10.80 · 0%Refactoring#73Obj. 10.80 · 0%Code review#72Obj. 11.20 · 0%Large-repo agent work#73Obj. 5.90 · 0%Frontend / UI#72Obj. 10.80 · 0%

Evidence state

Signal coverage

Benchmarks: 2
Rank points: 8
Usage: 2
Agent: 0
Sources: 3

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: —
Artificial Analysis: 14.4
Openrouter Usage: 0.3
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#73 · 7

Aug 1#73 · 7

Aug 1#73 · 7

Jul 31#73 · 7

Jul 31#73 · 7

Jul 31#73 · 7

Usage signals

OpenRouter0.3%

Overall0.2%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

Official NVIDIA Nemotron 3 Nano model card documents the current efficient open model.Artificial Analysis Coding Agents · ok WebDev Arena · ok NVIDIA Nemotron 3 Nano model card · ok