Mistral AI model product
Magistral Small
1 (2503).
Updated Oct 23, 2026. Default version: Magistral Small 2506
LLMBoard Score17.4Magistral Small 2506
Coverage60%4 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Magistral Small Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Magistral Small Benchmark Results
Benchmark scores for Magistral Small 2506.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAIME 2024 | Score70.68% | Rank41 | Participants54 | Percentile24.53% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score51.30% | Rank46 | Participants76 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score41.33% | Rank60 | Participants96 | Percentile37.89% | EvidenceB | EvaluatedN/A |
| BenchmarkAIME 2025 | Score62.76% | Rank103 | Participants122 | Percentile15.70% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score0.00% | Rank130 | Participants200 | Percentile35.18% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score7.55% | Rank136 | Participants200 | Percentile32.16% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score18.02% | Rank140 | Participants201 | Percentile30.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score64.14% | Rank149 | Participants199 | Percentile25.25% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score68.18% | Rank156 | Participants256 | Percentile39.22% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score24.76% | Rank162 | Participants168 | Percentile3.59% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score0.00% | Rank181 | Participants193 | Percentile6.25% | EvidenceB | EvaluatedN/A |
Magistral Small Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorycreative writing | Rank21 | Rating / score1,185.31 | Votes442 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank21 | Rating / score1,186.90 | Votes442 | ObservationsN/A | Result date |
Magistral Small Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.50 input, $1.5 output per 1M via IO.NET
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNvidia | Provider model IDmistralai/magistral-small-2506 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context32.8K | Updated |
| ProviderIO.NET | Provider model IDmistralai/Magistral-Small-2506 | Regionglobal | Input / 1M$0.50 | Output / 1M$1.5 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Magistral Small Runtime Performance
Provider-specific output speed and catalog latency for Magistral Small 2506. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Magistral Small Specifications
Technical details for the model's default version.
- Version
- Magistral Small 2506
- Released
- Jun 10, 2025
- Knowledge cutoff
- Jun 1, 2025
- Parameters
- 24B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Magistral Small Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMagistral Small 2506 | Released | LLMBoard17.45 | Parameters24B | ContextN/A | Max outputN/A | Open weightsYes | LicenseApache 2.0 |
Models similar to Magistral Small
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Magistral Medium
Mistral AI
MA
Min istral 3
Mistral AI
MA
Pixtral Large
Mistral AI
MA
Mistral Large 3
Mistral AI
MA
Devstral Small 1.1
Mistral AI
MA
Mistral Small 3.2 24B
Mistral AI
What is Magistral Small?
Key information about Magistral Small and its available data.
Magistral Small is a large language model from Mistral AI with added reasoning capabilities, trained using supervised fine-tuning from Magistral Medium traces and reinforcement learning. Once quantized, it can be deployed locally on a single RTX 4090 or a MacBook with 32GB of RAM.
Data as of 2026-10-22.
FAQ
Common questions about Magistral Small.
When was Magistral Small released?
Magistral Small's default version was released on Jun 10, 2025.
How much does Magistral Small cost?
No official standard PAYG price is currently available for Magistral Small. The lowest tracked third-party offer starts at $0.50 input and $1.5 output via IO.NET.
Who created Magistral Small?
Magistral Small was created by Mistral AI.
What is the context window for Magistral Small?
A context window is not available for the default version.
Is Magistral Small open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Magistral Small?
2 provider offerings are linked to the default version.