What is the IQ of Nanbeige 4.3 33B?

Nanbeige 4.3 33B does not yet have an estimated IQ. AI IQ publishes a composite score once a model has source-backed benchmark results in at least two of its seven capability dimensions.

What is Nanbeige 4.3 33B best at?

There isn't any published benchmark data to judge that yet. None of the seven dimensions AI IQ scores has a measured result for Nanbeige 4.3 33B, so its strengths and weaknesses can't be compared with other models.

What is the EQ of Nanbeige 4.3 33B?

Nanbeige 4.3 33B 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 Nanbeige 4.3 33B. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has Nanbeige 4.3 33B been tested on?

None yet. Nanbeige 4.3 33B has no published results on the 39 benchmarks behind AI IQ's Composite IQ. AI IQ only uses published, source-backed results, so its profile fills in as evaluations of this model appear.

How much does Nanbeige 4.3 33B cost?

AI IQ doesn't have a verified standard per-token API price for Nanbeige 4.3 33B, so it can't calculate an effective cost. This is common for models offered only through subscriptions, restricted-access programs, or self-hosting.

Is Nanbeige 4.3 33B open source?

Yes — Nanbeige 4.3 33B is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.

Who developed Nanbeige 4.3 33B?

Nanbeige 4.3 33B was developed by Nanbeige, based in China.

When was Nanbeige 4.3 33B released?

Nanbeige 4.3 33B was publicly released on October 25, 2026.

How large is the context window of Nanbeige 4.3 33B?

Nanbeige 4.3 33B supports a context window of 524,288 tokens — the amount of text it can consider in a single request.

How fast is Nanbeige 4.3 33B?

AI IQ doesn't have independent speed measurements for Nanbeige 4.3 33B yet. Speed comes from independent tests of a model's hosted API, which aren't available for every model — especially new, restricted-access, or self-hosted ones.

NanbeigeReleased Oct 25, 2026

NewOpen weights

Nanbeige 4.3 33B

Nanbeige 4.3 33B doesn't have a Composite IQ yet. A score needs measured results in at least two of the seven dimensions, and none have published results so far.

Composite IQ ?

—

Not yet ranked

0 of 7 dimensions measured; at least 2 are needed.

Effective cost

Not priced

No standard API rate

Speed

Not measured

No speed data yet

Context

524Ktokens

524,288 tokens in

Evidence

0of 7 dims

0 of 39 benchmarks

Compare with fable-5.2

IQ profile

Seven dimensions, averaged equally into Composite IQ

Profile not available yetThe radar appears once at least two dimensions have measured benchmark results.

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

99estimated

#77 / 209

0/5

-33

Mathematical ReasoningMath

—

0/5

—

Academic ReasoningAcademic

100estimated

#188 / 211

0/6

-35

Programmatic ReasoningCoding

—

0/6

—

Computer UseComputer Use

—

0/5

—

ReliabilityReliability

—

0/6

—

Knowledge WorkKnowledge Work

—

0/6

—

Nanbeige 4.3 33BTop-10 median#1 in dimension100 = average human

Benchmark results

0 of 39 Composite IQ benchmarks have a published result for Nanbeige 4.3 33B. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 99 · estimatedNo published results0/5

No published results yet for Abstract Reasoning. The 99 shown is estimated from Nanbeige 4.3 33B'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 no scoreNo published results0/5

No published results yet for Mathematical Reasoning. How estimates work

FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArenaAIME

Academic Reasoning IQ 100 · estimatedNo published results0/6

No published results yet for Academic Reasoning. The 100 shown is estimated from Nanbeige 4.3 33B's other dimensions and will be replaced as results come in. How estimates work

Humanity's Last ExamGPQA DiamondCritPtSciCodeMMLU-ProMMMU-Pro

Programmatic Reasoning no scoreNo published results0/6

No published results yet for Programmatic Reasoning. How estimates work

LiveCodeBenchIOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode

Computer Use no scoreNo published results0/5

No published results yet for Computer Use. How estimates work

BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability no scoreNo published results0/6

No published results yet for Reliability. How estimates work

SimpleQA VerifiedaaOmniscienceBullshitBench v2IFBenchAA Long Context Reasoning v1.1FACTS Grounding

Knowledge Work no scoreNo published results0/6

No published results yet for Knowledge Work. How estimates work

AA-Briefcase v1.1GDPval-AA v2.1AutomationBench-AAGDP.pdfAA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Facts from the publisher's announcement and documentation.

Released: Oct 25, 2026
Developer: Nanbeige
Access: Nanbeige announced Nanbeige4.3-33B on October 25, 2026. The exact Nanbeige/Nanbeige4.3-33B weights are downloadable for local deployment under Apache 2.0.
Weights: Open weightsDownloadable and self-hostable
Inputs: text
Context: 524,288 tokens
API price: No per-token rateNo current standard hosted token price has been verified for this exact checkpoint. The weights can be downloaded for local deployment.

What Nanbeige says

Dense 33-billion-parameter model intended for agentic coding and professional tasks.
The publisher model card specifies up to 524,288 tokens of context and supports configurable thinking and tool-use templates.

Limitations

No current standard hosted token price is verified for this exact checkpoint; downloadable weights do not establish an API price.
The model card's benchmark results use publisher-selected settings and harnesses; compatible independent AI IQ benchmark observations have not been verified.

Publisher statements, not AI IQ measurements.

Sourcesx.com/nanbeige/status/2114328933181333798 huggingface.co/Nanbeige/Nanbeige4.3-33B

About this score

How much of Nanbeige 4.3 33B's IQ is measured, and how the rest is estimated.

0/ 39benchmark results

0/ 7dimensions measured

2estimated

0/5Abstract

0/5Math

0/6Academic

0/6Coding

0/5Computer Use

0/6Reliability

0/6Knowledge 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 Academic Reasoning have no published results yet, so their IQ is estimated from Nanbeige 4.3 33B'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 Nanbeige 4.3 33B

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

#1 overall

fable-5.2

IQ144Effective cost$73.69

IQ141Effective cost$6.34

#4 overall

opus-5.5

IQ140Effective cost$35.97

#5 overall

Gemini 4 Argon

IQ139

Nanbeige 4.3 33BComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about Nanbeige 4.3 33B, 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 Nanbeige 4.3 33B?: Nanbeige 4.3 33B does not yet have an estimated IQ. AI IQ publishes a composite score once a model has source-backed benchmark results in at least two of its seven capability dimensions.
What is Nanbeige 4.3 33B best at?: There isn't any published benchmark data to judge that yet. None of the seven dimensions AI IQ scores has a measured result for Nanbeige 4.3 33B, so its strengths and weaknesses can't be compared with other models.
What is the EQ of Nanbeige 4.3 33B?: Nanbeige 4.3 33B 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 Nanbeige 4.3 33B. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has Nanbeige 4.3 33B been tested on?: None yet. Nanbeige 4.3 33B has no published results on the 39 benchmarks behind AI IQ's Composite IQ. AI IQ only uses published, source-backed results, so its profile fills in as evaluations of this model appear.
How much does Nanbeige 4.3 33B cost?: AI IQ doesn't have a verified standard per-token API price for Nanbeige 4.3 33B, so it can't calculate an effective cost. This is common for models offered only through subscriptions, restricted-access programs, or self-hosting.
Is Nanbeige 4.3 33B open source?: Yes — Nanbeige 4.3 33B is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed Nanbeige 4.3 33B?: Nanbeige 4.3 33B was developed by Nanbeige, based in China.
When was Nanbeige 4.3 33B released?: Nanbeige 4.3 33B was publicly released on October 25, 2026.
How large is the context window of Nanbeige 4.3 33B?: Nanbeige 4.3 33B supports a context window of 524,288 tokens — the amount of text it can consider in a single request.
How fast is Nanbeige 4.3 33B?: AI IQ doesn't have independent speed measurements for Nanbeige 4.3 33B yet. Speed comes from independent tests of a model's hosted API, which aren't available for every model — especially new, restricted-access, or self-hosted ones.