Mistral Small 4
Mistral Small 4 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.
IQ profile
IQ dimensions
Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.
Benchmark results
0 of 39 Composite IQ benchmarks have a published result for Mistral Small 4. Benchmarks without a result stay listed so gaps are visible.
Abstract Reasoning IQ 78 · estimatedNo published results0/5
Mathematical Reasoning no scoreNo published results0/5
Academic Reasoning IQ 100 · estimatedNo published results0/6
Programmatic Reasoning no scoreNo published results0/6
Computer Use no scoreNo published results0/5
Reliability no scoreNo published results0/6
Knowledge Work no scoreNo published results0/6
Release & availability
Facts from the publisher's announcement and documentation.
- Released
- Developer
- Mistral
- Access
- Available through the Mistral API and as downloadable weights.
- Weights
- Open weightsDownloadable and self-hostable
- Inputs
- textimage
- Context
- 256,000 tokens
- API price
- $0.15 in · $0.60 outper 1M tokens · full pricing
What Mistral says
- Mistral announced Small 4 on March 16, 2026 as a multimodal model with configurable reasoning effort.
- The model has 119B total parameters, 6B active parameters and a 256K-token context window.
Limitations
- Benchmark results at one reasoning effort must not be assumed to describe another.
- Local deployment requires substantial accelerator capacity.
Publisher statements, not AI IQ measurements.
About this score
How much of Mistral Small 4's IQ is measured, and how the rest is estimated.
Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.
Abstract Reasoning and Academic Reasoning have no published results yet, so their IQ is estimated from Mistral Small 4's other dimensions.
Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.
Compare Mistral Small 4
Side-by-side pages for the models it is most often weighed against.
Frequently asked questions
Quick answers about Mistral Small 4, 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 Mistral Small 4?
- Mistral Small 4 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 Mistral Small 4 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 Mistral Small 4, so its strengths and weaknesses can't be compared with other models.
- What is the EQ of Mistral Small 4?
- Mistral Small 4 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 Mistral Small 4. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
- Which benchmarks has Mistral Small 4 been tested on?
- None yet. Mistral Small 4 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 Mistral Small 4 cost?
- Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.5714 per million input-plus-output tokens.
- Is Mistral Small 4 open source?
- Yes — Mistral Small 4 is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
- Who developed Mistral Small 4?
- Mistral Small 4 was developed by Mistral, based in France.
- When was Mistral Small 4 released?
- Mistral Small 4 was publicly released on March 16, 2026.
- How large is the context window of Mistral Small 4?
- Mistral Small 4 supports a context window of 256,000 tokens — the amount of text it can consider in a single request.
- How fast is Mistral Small 4?
- AI IQ doesn't have independent speed measurements for Mistral Small 4 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.