Mistral AI model product
Mistral Small 3.2 24B
1-24B-Instruct-2503.
Updated Oct 23, 2026. Default version: Mistral Small 3.2 24B Instruct
LLMBoard Score13.8Mistral Small 3.2 24B Instruct
Coverage80%12 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
Mistral Small 3.2 24B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Mistral Small 3.2 24B Benchmark Results
Benchmark scores for Mistral Small 3.2 24B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkHumanEval Plus | Score92.90% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkIF | Score84.78% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMBPP Plus | Score78.33% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWild Bench | Score65.33% | Rank04 | Participants8 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkDocVQA | Score94.86% | Rank05 | Participants28 | Percentile85.19% | EvidenceC | Evaluated |
| BenchmarkAI2D | Score92.91% | Rank06 | Participants35 | Percentile85.29% | EvidenceC | Evaluated |
| BenchmarkChartQA | Score87.40% | Rank08 | Participants26 | Percentile72.00% | EvidenceC | Evaluated |
| BenchmarkArena Hard | Score43.10% | Rank22 | Participants27 | Percentile19.23% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score67.09% | Rank22 | Participants40 | Percentile46.15% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score12.10% | Rank39 | Participants47 | Percentile17.39% | EvidenceC | Evaluated |
| BenchmarkMATH | Score69.42% | Rank40 | Participants71 | Percentile44.29% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score62.50% | Rank44 | Participants66 | Percentile33.85% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score80.50% | Rank60 | Participants103 | Percentile42.16% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score27.00% | Rank74 | Participants96 | Percentile23.16% | EvidenceB | EvaluatedN/A |
| BenchmarkAA SciCode Subtasks | Score28.59% | Rank81 | Participants89 | Percentile9.09% | EvidenceB | EvaluatedN/A |
| BenchmarkMMLU-Pro | Score69.06% | Rank95 | Participants142 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score33.47% | Rank142 | Participants168 | Percentile15.57% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score0.00% | Rank149 | Participants200 | Percentile25.63% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score20.33% | Rank162 | Participants193 | Percentile16.15% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score14.83% | Rank169 | Participants201 | Percentile16.00% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score4.31% | Rank172 | Participants200 | Percentile14.07% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score50.51% | Rank173 | Participants199 | Percentile13.13% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score46.13% | Rank210 | Participants256 | Percentile18.04% | EvidenceC | Evaluated |
Mistral Small 3.2 24B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Mistral Small 3.2 24B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.0938 input, $0.25 output per 1M via OpenRouter
- Tracked offerings
- 8
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderMeganova | Provider model IDmistralai/Mistral-Small-3.2-24B-Instruct-2506 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context32.8K | Updated |
| ProviderOpenRouter | Provider model IDmistralai/mistral-small-3.2-24b-instruct | Regionglobal | Input / 1M$0.0938 | Output / 1M$0.25 | Context256K | Updated |
| ProviderVenice AI | Provider model IDmistral-small-3-2-24b-instruct | Regionglobal | Input / 1M$0.0938 | Output / 1M$0.25 | Context256K | Updated |
| ProviderCortecs | Provider model IDmistral-small-3.2-24b-instruct-2506 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.312 | Context131K | Updated |
| ProviderOVHcloud AI Endpoints | Provider model IDmistral-small-3.2-24b-instruct-2506 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.31 | Context131.1K | Updated |
| ProviderKilo Gateway | Provider model IDmistralai/mistral-small-3.2-24b-instruct | Regionglobal | Input / 1M$0.10 | Output / 1M$0.30 | Context256K | Updated |
| ProviderScaleway | Provider model IDmistral-small-3.2-24b-instruct-2506 | Regionglobal | Input / 1M$0.1682 | Output / 1M$0.3925 | Context128K | Updated |
| ProviderGreenPT | Provider model IDmistral-small-3.2-24b-instruct-2506 | Regionglobal | Input / 1M$0.228 | Output / 1M$0.456 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Mistral Small 3.2 24B Runtime Performance
Provider-specific output speed and catalog latency for Mistral Small 3.2 24B Instruct. 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.
Mistral Small 3.2 24B Specifications
Technical details for the model's default version.
- Version
- Mistral Small 3.2 24B Instruct
- Released
- Jun 20, 2025
- Knowledge cutoff
- Oct 1, 2023
- Parameters
- 23.6B
- Context window
- 128K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Mistral Small 3.2 24B 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 |
|---|
| VersionMistral Small 3.2 24B Instruct | Released | LLMBoard13.75 | Parameters23.6B | Context128K | Max output128K | Open weightsYes | LicenseApache 2.0 |
Models similar to Mistral Small 3.2 24B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Devstral Small 1.1
Mistral AI
MA
Mistral Large 3
Mistral AI
MA
Magistral Medium
Mistral AI
MA
Magistral Small
Mistral AI
MA
Min istral 3
Mistral AI
MA
Pixtral Large
Mistral AI
What is Mistral Small 3.2 24B?
Key information about Mistral Small 3.2 24B and its available data.
2 24B is a large language model from Mistral AI. 1-24B-Instruct-2503.
Data as of 2026-10-22.
FAQ
Common questions about Mistral Small 3.2 24B.
When was Mistral Small 3.2 24B released?
Mistral Small 3.2 24B's default version was released on Jun 20, 2025.
How much does Mistral Small 3.2 24B cost?
No official standard PAYG price is currently available for Mistral Small 3.2 24B. The lowest tracked third-party offer starts at $0.0938 input and $0.25 output via OpenRouter.
Who created Mistral Small 3.2 24B?
Mistral Small 3.2 24B was created by Mistral AI.
What is the context window for Mistral Small 3.2 24B?
The default version has a 128K token context window.
Is Mistral Small 3.2 24B open weight?
Yes. The default version is marked as open weight under Apache 2.0.