Nemotron 3 Super-120B-A12B

Name: Nemotron 3 Super-120B-A12B
Author: NVIDIA AI

Released

2026-03-11

Last refreshed

2026-06-29

Status

Researched 121d ago

Open weightsCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool use

NVIDIA AI releases · 19 in the last 12 months · this family litChangelog →

Specifications

Family: Nemotron 3
Released: 2026-03-11
Context: 1.05m
Parameters: 120B
Architecture: Decoder Only
Specialization: general
Openness: Open weights
License: NVIDIA Open ModelCommercial use: permitted
Weights: Available
Code: Unknown

Created by

NVIDIA AI

Accelerated AI for enterprise solutions

Santa Clara, California, United States

Founded 2015

Website

Pricing

Output / 1M

$0.450

Input / 1M

$0.090

Cheapest of 6 routes · OpenRouter

Providers(6)

Cloudflare Workers AI DeepInfra NVIDIA NIM OpenRouter Fireworks AI Vercel AI Gateway

View 6 provider routes

Links

Website HuggingFace

About

NVIDIA Nemotron 3 Super-120B-A12B is a 120B total / 12B active hybrid Latent MoE model with interleaved Mamba-2 and MoE layers for agentic, reasoning, and conversational tasks. Fireworks lists the NVFP4 variant for on-demand deployment with 262k context.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ B

RAG

Q/$ D

Agents

Q/$ A

Provider price ladder

Compare all 6

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Cache	Route
OpenRouter	$0.090	$0.450	-	Serverless
DeepInfra	$0.100	$0.500	-	Serverless
NVIDIA NIM	$0.100	$0.500	read $0.100	Serverless
Vercel AI Gateway	$0.150	$0.650	-	Serverless

Available via routers & gateways(2)

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughFireworks AI

NVIDIA LLM Router Blueprint

Router

NVIDIA's open-source AI blueprint for LLM routing that selects the optimal model per prompt via intent classification or neural auto-routing; being deprecated 2026-06-20.

Free OSSNVIDIA NIM

Capabilities

Structured Outputs

Benchmark peer barsfor Coding

SWE-bench VerifiedRank 73 of 81

Claude Fable 5

96.0

Claude Opus 5

96.0

Claude Mythos Preview

93.9

Claude Opus 4.8

88.6

Nemotron 3 Super-120B-A12Bcurrent

60.5

LiveCodeBenchRank 34 of 56

DeepSeek V4 Pro

93.5

Gemini 3.1 Pro Preview

91.7

DeepSeek V4 Flash

91.6

Qwen3.7-Max

91.6

Nemotron 3 Super-120B-A12Bcurrent

78.4

Benchmark scores(7)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.

Benchmark	Score	Version	Evaluation	Source
Google-Proof Q&A	80.0	diamondObserved 2026-04-18	—	Source
AIME 2025	90.2	Widely reported from NVIDIA launch materials (accuracy)Observed 2026-06-07	—	Source
LiveCodeBench	78.4	LiveCodeBench v6 (accuracy)Observed 2026-06-07	—	Source
MMLU PRO	83.6	From official HuggingFace model card (accuracy)Observed 2026-06-07	—	Source
RULER	96.3	RULER (accuracy)Observed 2026-06-07	—	Source
SWE-bench Verified	60.5	SWE-bench Verified (resolved)Observed 2026-06-07	—	Source
τ-bench	61.1	TauBench V2 average (airline 56 (accuracy)Observed 2026-06-07	—	Source