MoondreamReleased Sep 18, 2025
Open weights
Moondream 3 Preview
Moondream 3 Preview 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 ?
—
Effective cost
$2.60/1M
$0.30 in · $2.50 out
Speed
Not measured
No speed data yet
Context
33Ktokens
32,768 tokens in
Evidence
0of 7 dims
0 of 39 benchmarks
IQ profile
Seven dimensions, averaged equally into Composite IQ
Profile not available yetThe radar appears once at least two dimensions have measured benchmark results.
MeasuredEstimated
#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
Moondream 3 PreviewTop-10 median#1 in dimension100 = average human
Benchmark results
0 of 39 Composite IQ benchmarks have a published result for Moondream 3 Preview. Benchmarks without a result stay listed so gaps are visible.
Abstract Reasoning IQ 73 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 73 shown is estimated from Moondream 3 Preview'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 Moondream 3 Preview'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
- Developer
- Moondream
- Access
- Downloadable preview weights and publisher playground; use is subject to Business Source License 1.1 with an additional use grant.
- Weights
- Open weightsDownloadable and self-hostable
- Inputs
- textimage
- Context
- 32,768 tokens
- API price
- $0.30 in · $2.50 outper 1M tokens · full pricing
What Moondream says
- A 9B-total, 2B-active mixture-of-experts vision-language model supporting visual questions, captioning, detection and pointing.
- The publisher card also documents text-only queries and selectable reasoning.
Limitations
- The license restricts competing paid hosted or embedded services without a separate agreement.
- The release is a preview; publisher-reported sampled evaluations are not imported as independent benchmark results.
Publisher statements, not AI IQ measurements.
About this score
How much of Moondream 3 Preview'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 Moondream 3 Preview'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.
Compare Moondream 3 Preview
Side-by-side pages for the models it is most often weighed against.
#1 overall
gpt-6.1-sol
IQ141Effective cost$6.30 2.4× pricier
US (Other) #1
Beam
IQ113
#2 overall
opus-5.5
IQ141Effective cost$35.73 13.7× pricier
#3 overall
Gemini 4 Argon
IQ140
#4 overall
gpt-6-astra
IQ140Effective cost$34.20 13.2× pricier
#5 overall
fable-5.1
IQ137Effective cost$90.99 35.0× pricier
Moondream 3 PreviewComparison model
Frequently asked questions
Quick answers about Moondream 3 Preview, 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 Moondream 3 Preview?
- Moondream 3 Preview 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 Moondream 3 Preview 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 Moondream 3 Preview, so its strengths and weaknesses can't be compared with other models.
- What is the EQ of Moondream 3 Preview?
- Moondream 3 Preview 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 Moondream 3 Preview. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
- Which benchmarks has Moondream 3 Preview been tested on?
- None yet. Moondream 3 Preview 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 Moondream 3 Preview cost?
- Moondream 3 Preview costs $0.30 per million input tokens and $2.50 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $2.60 per million input-plus-output tokens.
- Is Moondream 3 Preview open source?
- Yes — Moondream 3 Preview is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
- Who developed Moondream 3 Preview?
- Moondream 3 Preview was developed by Moondream, based in the United States.
- When was Moondream 3 Preview released?
- Moondream 3 Preview was publicly released on September 18, 2025.
- How large is the context window of Moondream 3 Preview?
- Moondream 3 Preview supports a context window of 32,768 tokens — the amount of text it can consider in a single request.
- How fast is Moondream 3 Preview?
- AI IQ doesn't have independent speed measurements for Moondream 3 Preview 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.