What is the IQ of nemotron-3-super?

nemotron-3-super has an estimated IQ of 101, which ranks #123 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-super best at?

Among the dimensions with published benchmark results, nemotron-3-super ranks highest in Reliability (IQ 112, #91 of 177) and Academic Reasoning (IQ 118, #109 of 203). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 99, #142 of 177).

What is the EQ of nemotron-3-super?

nemotron-3-super 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-super. 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-super been tested on?

nemotron-3-super has published results on 14 of the 39 benchmarks behind AI IQ's Composite IQ, including BullshitBench v2, IFBench, CritPt, GPQA Diamond and Humanity's Last Exam.

How much does nemotron-3-super cost?

nemotron-3-super costs $0.30 per million input tokens and $0.90 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $3.30 per million input-plus-output tokens.

Is nemotron-3-super open source?

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

Who developed nemotron-3-super?

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

When was nemotron-3-super released?

nemotron-3-super was publicly released on March 11, 2026.

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

nemotron-3-super 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-super?

In independent measurements, nemotron-3-super generates about 160 tokens per second, with a typical response time of about 17 seconds.

NVIDIAReleased Mar 11, 2026

Open weights

nemotron-3-super

Its best results are in Reliability (#91 of 177) and Academic Reasoning (#109 of 203); weakest in Programmatic Reasoning (#142 of 177). Abstract Reasoning and Computer Use are estimated, because no results are published yet.

Composite IQ ?

101

#123 of 176 ranked models · ahead of 30%

US (Other)'s #8 model, behind Beam (114)

Effective cost

$3.30/1M

$0.30 in · $0.90 out

Speed

160tok/s

17s typical response

Context

1Mtokens

1,000,000 tokens in

Evidence

5of 7 dims

14 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

80estimated

#157 / 201

0/5

-46.5

Mathematical ReasoningMath

109measured

#99 / 176

1/5

-38

Academic ReasoningAcademic

118measured

#109 / 203

4/6

-17.5

Programmatic ReasoningCoding

99measured

#142 / 177

1/6

-50.5

Computer UseComputer Use

94estimated

#135 / 176

0/5

-49

ReliabilityReliability

112measured

#91 / 177

4/6

-22

Knowledge WorkKnowledge Work

98measured

#124 / 176

4/6

-33.5

nemotron-3-super95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

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

Abstract Reasoning IQ 80 · estimatedNo published results0/5

No published results yet for Abstract Reasoning. The 80 shown is estimated from nemotron-3-super'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 109 · measuredBest: #48 of 64 on MathArena1/5

BenchmarkScorePercentileRankLeader · source

MathArena

Full source leaderboard reconciliation · Oct 28

16.2%

#48 / 64

Leader gpt-6.1-sol · 84.0%
Full source leaderboard reconciliation · Oct 28

Not yet reported

FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1AIME

Academic Reasoning IQ 118 · measuredBest: #93 of 159 on CritPt4/6

BenchmarkScorePercentileRankLeader · source

CritPt

Artificial Analysis v4.3.2 · Oct 27

3.1%

#93 / 159

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

GPQA Diamond

Artificial Analysis v4.3.2 · Oct 27

80.0%

#101 / 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

20.8%

#117 / 167

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

SciCode

Artificial Analysis v4.3.2 · Oct 27

36.2%

#143 / 167

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

Not yet reported

MMLU-ProMMMU-Pro

Programmatic Reasoning IQ 99 · measuredBest: #99 of 104 on Terminal-Bench 4.01/6

BenchmarkScorePercentileRankLeader · source

Terminal-Bench 4.0

Artificial Analysis v4.3.2 · Oct 27

0.0%

#99 / 104

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

Not yet reported

LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 94 · estimatedNo published results0/5

No published results yet for Computer Use. The 94 shown is estimated from nemotron-3-super's other dimensions and will be replaced as results come in. How estimates work

BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 112 · measuredBest: #33 of 83 on BullshitBench v24/6

BenchmarkScorePercentileRankLeader · source

BullshitBench v2

Full source leaderboard reconciliation · Oct 23

54.0%

#33 / 83

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

IFBench

Artificial Analysis v4.3.2 · Oct 27

71.5%

#39 / 96

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

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 27

65.7%

#121 / 154

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

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

-41.5

#140 / 158

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

Not yet reported

SimpleQA VerifiedFACTS Grounding

Knowledge Work IQ 98 · measuredBest: #81 of 106 on AutomationBench-AA4/6

BenchmarkScorePercentileRankLeader · source

AutomationBench-AA

Artificial Analysis v4.3.2 · Oct 27

3.8%

#81 / 106

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

GDP.pdf

Artificial Analysis v4.3.2 · Oct 27

2.6%

#94 / 106

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

GDPval-AA v2.1 normalized score

Artificial Analysis v4.3.2 · Oct 20

0.0%

#119 / 124

Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 20

AA-Briefcase v1.1 Elo

Artificial Analysis v4.3.2 · Oct 27

0.0

#111 / 111

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

Not yet reported

AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Release details on record for this model.

Released: Mar 11, 2026
Developer: NVIDIA
Weights: Open weightsDownloadable and self-hostable
Context: 1,000,000 tokens
API price: $0.30 in · $0.90 outper 1M tokens · full pricing

About this score

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

14/ 39benchmark results

5/ 7dimensions measured

2estimated

0/5Abstract

1/5Math

4/6Academic

1/6Coding

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-super'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-super

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

#1 overall

gpt-6.1-sol

IQ141 40 higherEffective cost$6.30 1.9× pricier

IQ101 same IQEffective cost$2.19 1.5× cheaper

Most similar profile

minimax-m2.7

IQ105 4 higherEffective cost$1.46 2.3× cheaper

Similar price

Hy4 Preview

IQ112 11 higherEffective cost$3.30 about the same

#2 overall

opus-5.5

IQ141 40 higherEffective cost$35.73 10.8× pricier

nemotron-3-superComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about nemotron-3-super, 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-super?: nemotron-3-super has an estimated IQ of 101, which ranks #123 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-super best at?: Among the dimensions with published benchmark results, nemotron-3-super ranks highest in Reliability (IQ 112, #91 of 177) and Academic Reasoning (IQ 118, #109 of 203). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 99, #142 of 177).
What is the EQ of nemotron-3-super?: nemotron-3-super 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-super. 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-super been tested on?: nemotron-3-super has published results on 14 of the 39 benchmarks behind AI IQ's Composite IQ, including BullshitBench v2, IFBench, CritPt, GPQA Diamond and Humanity's Last Exam.
How much does nemotron-3-super cost?: nemotron-3-super costs $0.30 per million input tokens and $0.90 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $3.30 per million input-plus-output tokens.
Is nemotron-3-super open source?: Yes — nemotron-3-super is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed nemotron-3-super?: nemotron-3-super was developed by NVIDIA, based in the United States.
When was nemotron-3-super released?: nemotron-3-super was publicly released on March 11, 2026.
How large is the context window of nemotron-3-super?: nemotron-3-super 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-super?: In independent measurements, nemotron-3-super generates about 160 tokens per second, with a typical response time of about 17 seconds.