What is the IQ of nemotron-3-nano?

nemotron-3-nano has an estimated IQ of 97, which ranks #143 out of 176 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.

What is nemotron-3-nano best at?

Among the dimensions with published benchmark results, nemotron-3-nano ranks highest in Mathematical Reasoning (IQ 112, #83 of 176) and Programmatic Reasoning (IQ 102, #116 of 177). Its lowest-ranked measured dimension is Reliability (IQ 98, #155 of 177).

What is the EQ of nemotron-3-nano?

nemotron-3-nano doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for nemotron-3-nano. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has nemotron-3-nano been tested on?

nemotron-3-nano has published results on 16 of the 39 benchmarks behind AI IQ's Composite IQ, including AIME, IFBench, MMLU-Pro, LiveCodeBench and CritPt.

How much does nemotron-3-nano cost?

nemotron-3-nano costs $0.05 per million input tokens and $0.20 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.1627 per million input-plus-output tokens.

Is nemotron-3-nano open source?

Yes — nemotron-3-nano is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.

Who developed nemotron-3-nano?

nemotron-3-nano was developed by NVIDIA, based in the United States.

When was nemotron-3-nano released?

nemotron-3-nano was publicly released on December 15, 2025.

How large is the context window of nemotron-3-nano?

nemotron-3-nano supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.

How fast is nemotron-3-nano?

In independent measurements, nemotron-3-nano generates about 276 tokens per second, with a typical response time of about 10 seconds.

NVIDIAReleased Dec 15, 2025

Open weights

nemotron-3-nano

Its best results are in Mathematical Reasoning (#83 of 176) and Programmatic Reasoning (#116 of 177); weakest in Reliability (#155 of 177). Abstract Reasoning and Computer Use are estimated, because no results are published yet.

Composite IQ ?

#143 of 176 ranked models · ahead of 19%

US (Other)'s #14 model, behind Beam (114)

Effective cost

$0.163/1M

$0.05 in · $0.20 out

Speed

276tok/s

10s typical response

Context

1Mtokens

1,000,000 tokens in

Evidence

5of 7 dims

16 of 39 benchmarks

Compare with gpt-6.1-solAPI pricing

IQ profile

Seven dimensions, averaged equally into Composite IQ

Compare shape with

MeasuredEstimated95% range

#1 in dimensionTop-10 median

IQ dimensions

Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.

DimensionIQPosition · 70–160RankEvidencevs Top 10

Abstract ReasoningAbstract

75estimated

#184 / 201

0/5

-51.5

Mathematical ReasoningMath

112measured

#83 / 176

1/5

-35

Academic ReasoningAcademic

107measured

#147 / 203

5/6

-28.5

Programmatic ReasoningCoding

102measured

#116 / 177

2/6

-47.5

Computer UseComputer Use

87estimated

#143 / 176

0/5

-56

ReliabilityReliability

98measured

#155 / 177

4/6

-36

Knowledge WorkKnowledge Work

95measured

#135 / 176

4/6

-36.5

nemotron-3-nano95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

16 of 39 Composite IQ benchmarks have a published result for nemotron-3-nano. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 75 · estimatedNo published results0/5

No published results yet for Abstract Reasoning. The 75 shown is estimated from nemotron-3-nano's other dimensions and will be replaced as results come in. How estimates work

ARC-AGI-3ARC-AGI-2ARC-AGI-1Chess PuzzlesMystery Game Puzzles

Mathematical Reasoning IQ 112 · measuredBest: #24 of 56 on AIME1/5

BenchmarkScorePercentileRankLeader · source

AIME

91.0%

#24 / 56

Leader gemini-3.1-pro · 98.1%

Not yet reported

FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArena

Academic Reasoning IQ 107 · measuredBest: #33 of 45 on MMLU-Pro5/6

BenchmarkScorePercentileRankLeader · source

MMLU-Pro

TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

79.4%

#33 / 45

Leader fable-5.1 · 92.4%
TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

CritPt

Artificial Analysis v4.3.2 · Oct 27

0.9%

#119 / 159

Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27

GPQA Diamond

Artificial Analysis v4.3.2 · Oct 27

75.7%

#118 / 147

Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

11.4%

#139 / 167

Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27

SciCode

Artificial Analysis v4.3.2 · Oct 27

30.6%

#155 / 167

Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

MMMU-Pro

Programmatic Reasoning IQ 102 · measuredBest: #45 of 61 on LiveCodeBench2/6

BenchmarkScorePercentileRankLeader · source

LiveCodeBench

Vals.ai · Aug 4

74.1%

#45 / 61

Leader Fugu Ultra v1.0 · 93.2%
Vals.ai · Aug 4

Terminal-Bench 4.0

Artificial Analysis v4.3.2 · Oct 27

0.0%

#98 / 104

Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

IOI V2ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 87 · estimatedNo published results0/5

No published results yet for Computer Use. The 87 shown is estimated from nemotron-3-nano's other dimensions and will be replaced as results come in. How estimates work

BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 98 · measuredBest: #43 of 96 on IFBench4/6

BenchmarkScorePercentileRankLeader · source

IFBench

Artificial Analysis v4.3.2 · Oct 27

71.1%

#43 / 96

Leader minimax-m3 · 82.9%
Artificial Analysis v4.3.2 · Oct 27

BullshitBench v2

Full source leaderboard reconciliation · Oct 23

10.0%

#76 / 83

Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 27

38.0%

#145 / 154

Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

-51.6

#151 / 158

Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

SimpleQA VerifiedFACTS Grounding

Knowledge Work IQ 95 · measuredBest: #98 of 106 on AutomationBench-AA4/6

BenchmarkScorePercentileRankLeader · source

AutomationBench-AA

Artificial Analysis v4.3.2 · Oct 27

1.0%

#98 / 106

Leader Gemini 4 Argon · 77.5%
Artificial Analysis v4.3.2 · Oct 27

GDPval-AA v2.1 normalized score

Artificial Analysis v4.3.2 · Oct 23

0.0%

#118 / 124

Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 23

AA-Briefcase v1.1 Elo

Artificial Analysis v4.3.2 · Oct 27

77.2

#107 / 111

Leader sonnet-5.5 · 1,812
Artificial Analysis v4.3.2 · Oct 27

GDP.pdf

Artificial Analysis v4.3.2 · Oct 27

1.0%

#103 / 106

Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Release details on record for this model.

Released: Dec 15, 2025
Developer: NVIDIA
Weights: Open weightsDownloadable and self-hostable
Context: 1,000,000 tokens
API price: $0.05 in · $0.20 outper 1M tokens · full pricing

About this score

How much of nemotron-3-nano's IQ is measured, and how the rest is estimated.

16/ 39benchmark results

5/ 7dimensions measured

2estimated

0/5Abstract

1/5Math

5/6Academic

2/6Coding

0/5Computer Use

4/6Reliability

4/6Knowledge Work

Bar height = share of benchmarks with resultsEstimatedNo score

Measured results are shown as published

Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.

Estimates fill the gaps

Abstract Reasoning and Computer Use have no published results yet, so their IQ is estimated from nemotron-3-nano's other dimensions.

A missing result is not a zero

Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.

Read the scoring methodology →

Compare nemotron-3-nano

Side-by-side pages for the models it is most often weighed against.

#1 overall

gpt-6.1-sol

IQ141 44 higherEffective cost$6.30 38.7× pricier

IQ94 3 lowerEffective cost$0.149 about the same

#2 overall

opus-5.5

IQ141 44 higherEffective cost$35.73 219.6× pricier

nemotron-3-nanoComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about nemotron-3-nano, drawn from the same data as the rest of this page.

How AI IQ scores models →Get this data from the API →

What is the IQ of nemotron-3-nano?: nemotron-3-nano has an estimated IQ of 97, which ranks #143 out of 176 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
What is nemotron-3-nano best at?: Among the dimensions with published benchmark results, nemotron-3-nano ranks highest in Mathematical Reasoning (IQ 112, #83 of 176) and Programmatic Reasoning (IQ 102, #116 of 177). Its lowest-ranked measured dimension is Reliability (IQ 98, #155 of 177).
What is the EQ of nemotron-3-nano?: nemotron-3-nano doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for nemotron-3-nano. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has nemotron-3-nano been tested on?: nemotron-3-nano has published results on 16 of the 39 benchmarks behind AI IQ's Composite IQ, including AIME, IFBench, MMLU-Pro, LiveCodeBench and CritPt.
How much does nemotron-3-nano cost?: nemotron-3-nano costs $0.05 per million input tokens and $0.20 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.1627 per million input-plus-output tokens.
Is nemotron-3-nano open source?: Yes — nemotron-3-nano is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed nemotron-3-nano?: nemotron-3-nano was developed by NVIDIA, based in the United States.
When was nemotron-3-nano released?: nemotron-3-nano was publicly released on December 15, 2025.
How large is the context window of nemotron-3-nano?: nemotron-3-nano supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is nemotron-3-nano?: In independent measurements, nemotron-3-nano generates about 276 tokens per second, with a typical response time of about 10 seconds.