What is the IQ of Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL has an estimated IQ of 108, which ranks #84 out of 168 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 3.5 Super VL best at?

Among the dimensions with published benchmark results, Nemotron 3.5 Super VL ranks highest in Academic Reasoning (IQ 127, #65 of 187) and Knowledge Work (IQ 111, #75 of 168). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 99, #137 of 169).

What is the EQ of Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL 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 3.5 Super VL. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has Nemotron 3.5 Super VL been tested on?

Nemotron 3.5 Super VL has published results on 10 of the 39 benchmarks behind AI IQ's Composite IQ, including CritPt, GDPval-AA v2.1 normalized score, SciCode, AA-Briefcase v1.1 Elo and AA Omniscience.

How much does Nemotron 3.5 Super VL cost?

AI IQ doesn't have a verified standard per-token API price for Nemotron 3.5 Super VL, so it can't calculate an effective cost. This is common for models offered only through subscriptions, restricted-access programs, or self-hosting.

Is Nemotron 3.5 Super VL open source?

Yes — Nemotron 3.5 Super VL is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.

Who developed Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL was developed by NVIDIA, based in the United States.

When was Nemotron 3.5 Super VL released?

Nemotron 3.5 Super VL was publicly released on October 15, 2026.

How large is the context window of Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.

How fast is Nemotron 3.5 Super VL?

In independent measurements, Nemotron 3.5 Super VL generates about 233 tokens per second, with a typical response time of about 12 seconds.

NVIDIAReleased Oct 15, 2026

NewOpen weights

Nemotron 3.5 Super VL

Its best results are in Academic Reasoning (#65 of 187) and Knowledge Work (#75 of 168); weakest in Programmatic Reasoning (#137 of 169). Three of seven dimensions are estimated, because no results are published yet.

Composite IQ ?

108

#84 of 168 ranked models · ahead of 50%

US (Other)'s #3 model, behind Beam (113)

Effective cost

Not priced

No standard API rate

Speed

233tok/s

12s typical response

Context

1Mtokens

1,000,000 tokens in

Evidence

4of 7 dims

10 of 39 benchmarks

Compare with gpt-6.1-sol

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

93estimated

#81 / 185

0/5

-35.5

Mathematical ReasoningMath

109estimated

#92 / 168

0/5

-37

Academic ReasoningAcademic

127measured

#65 / 187

3/6

-8.5

Programmatic ReasoningCoding

99measured

#137 / 169

1/6

-50

Computer UseComputer Use

102estimated

#104 / 168

0/5

-38.5

ReliabilityReliability

112measured

#80 / 168

2/6

-20.5

Knowledge WorkKnowledge Work

111measured

#75 / 168

4/6

-20

Nemotron 3.5 Super VL95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

10 of 39 Composite IQ benchmarks have a published result for Nemotron 3.5 Super VL. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 93 · estimatedNo published results0/5

No published results yet for Abstract Reasoning. The 93 shown is estimated from Nemotron 3.5 Super VL'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 · estimatedNo published results0/5

No published results yet for Mathematical Reasoning. The 109 shown is estimated from Nemotron 3.5 Super VL's other dimensions and will be replaced as results come in. How estimates work

FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArenaAIME

Academic Reasoning IQ 127 · measuredBest: #56 of 153 on CritPt3/6

BenchmarkScorePercentileRankLeader · source

CritPt

Artificial Analysis v4.3.2 · Oct 16

10.6%

#56 / 153

Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 16

SciCode

Artificial Analysis v4.3.2 · Oct 16

47.8%

#72 / 161

Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 16

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 16

30.7%

#77 / 161

Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 16

Not yet reported

GPQA DiamondMMLU-ProMMMU-Pro

Programmatic Reasoning IQ 99 · measuredBest: #92 of 99 on Terminal-Bench 4.01/6

BenchmarkScorePercentileRankLeader · source

Terminal-Bench 4.0

Artificial Analysis v4.3.2 · Oct 16

0.0%

#92 / 99

Leader sonnet-5.5 · 63.6%
Artificial Analysis v4.3.2 · Oct 16

Not yet reported

LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 102 · estimatedNo published results0/5

No published results yet for Computer Use. The 102 shown is estimated from Nemotron 3.5 Super VL'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: #72 of 152 on AA Omniscience2/6

BenchmarkScorePercentileRankLeader · source

AA Omniscience

Artificial Analysis v4.3.2 · Oct 16

-4.2

#72 / 152

Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 16

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 16

69.0%

#110 / 148

Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 16

Not yet reported

SimpleQA VerifiedBullshitBench v2IFBenchFACTS Grounding

Knowledge Work IQ 111 · measuredBest: #52 of 119 on GDPval-AA v2.1 normalized score4/6

BenchmarkScorePercentileRankLeader · source

GDPval-AA v2.1 normalized score

Artificial Analysis v4.3.2 · Oct 16

33.1%

#52 / 119

Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 16

AA-Briefcase v1.1 Elo

Artificial Analysis v4.3.2 · Oct 16

999

#47 / 105

Leader sonnet-5.5 · 1,817
Artificial Analysis v4.3.2 · Oct 16

AutomationBench-AA

Artificial Analysis v4.3.2 · Oct 16

14.8%

#59 / 101

Leader Gemini 4 Argon · 77.5%
Artificial Analysis v4.3.2 · Oct 16

GDP.pdf

Artificial Analysis v4.3.2 · Oct 16

8.0%

#63 / 100

Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 16

Not yet reported

AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Facts from the publisher's announcement and documentation.

Released: Oct 15, 2026
Developer: NVIDIA
Access: OpenMDW-1.1 weights available for download; hosted through NVIDIA NIM and inference partners.
Weights: Open weightsDownloadable and self-hostable
Inputs: textimagevideo
Context: 1,000,000 tokens
API price: No per-token rateNo current standard hosted token price has been verified for this exact checkpoint; weight availability is separate from hosted API pricing.

What NVIDIA says

NVIDIA released this vision-language model on October 15, 2026.
Hybrid Mamba-Transformer mixture of experts with 120B total and 12B active parameters.

Limitations

Weights are governed by OpenMDW-1.1.
Input images and video produce text responses; audio input is not supported.

Publisher statements, not AI IQ measurements.

Sourcesblogs.nvidia.com/blog/nemotron-3-5-super-vl huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

About this score

How much of Nemotron 3.5 Super VL's IQ is measured, and how the rest is estimated.

10/ 39benchmark results

4/ 7dimensions measured

3estimated

0/5Abstract

0/5Math

3/6Academic

1/6Coding

0/5Computer Use

2/6Reliability

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, Mathematical Reasoning and Computer Use have no published results yet, so their IQ is estimated from Nemotron 3.5 Super VL's other dimensions. Missing benchmarks can also draw on its predecessor, Nemotron 3 Super; a predecessor is an estimation input, not evidence that this model has the predecessor's measured results.

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 3.5 Super VL

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

#1 overall

gpt-6.1-sol

IQ141 33 higherEffective cost$6.29

Predecessor

nemotron-3-super

IQ102 6 lowerEffective cost$3.30

IQ108 same IQEffective cost$44.74

Most similar profile

Agnes 2.5 Pro Beta

IQ110 2 higherEffective cost$0.82

#2 overall

opus-5.5

IQ141 33 higherEffective cost$35.67

Nemotron 3.5 Super VLComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about Nemotron 3.5 Super VL, 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 3.5 Super VL?: Nemotron 3.5 Super VL has an estimated IQ of 108, which ranks #84 out of 168 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 3.5 Super VL best at?: Among the dimensions with published benchmark results, Nemotron 3.5 Super VL ranks highest in Academic Reasoning (IQ 127, #65 of 187) and Knowledge Work (IQ 111, #75 of 168). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 99, #137 of 169).
What is the EQ of Nemotron 3.5 Super VL?: Nemotron 3.5 Super VL 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 3.5 Super VL. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has Nemotron 3.5 Super VL been tested on?: Nemotron 3.5 Super VL has published results on 10 of the 39 benchmarks behind AI IQ's Composite IQ, including CritPt, GDPval-AA v2.1 normalized score, SciCode, AA-Briefcase v1.1 Elo and AA Omniscience.
How much does Nemotron 3.5 Super VL cost?: AI IQ doesn't have a verified standard per-token API price for Nemotron 3.5 Super VL, so it can't calculate an effective cost. This is common for models offered only through subscriptions, restricted-access programs, or self-hosting.
Is Nemotron 3.5 Super VL open source?: Yes — Nemotron 3.5 Super VL is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed Nemotron 3.5 Super VL?: Nemotron 3.5 Super VL was developed by NVIDIA, based in the United States.
When was Nemotron 3.5 Super VL released?: Nemotron 3.5 Super VL was publicly released on October 15, 2026.
How large is the context window of Nemotron 3.5 Super VL?: Nemotron 3.5 Super VL supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is Nemotron 3.5 Super VL?: In independent measurements, Nemotron 3.5 Super VL generates about 233 tokens per second, with a typical response time of about 12 seconds.