Mistral AI model product
Mistral Small 3 24B
3 70B or Qwen 32B, and is an excellent open replacement for opaque proprietary models like GPT4o-mini.
Updated Aug 17, 2026. Default version: Mistral Small 3 24B Instruct
LLMBoard Score6.7Mistral Small 3 24B Instruct
Coverage100%8 benchmark families
Context window32KTokens
Official input priceN/AOfficial price unavailable
Mistral Small 3 24B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Mistral Small 3 24B Benchmark Results
Benchmark scores for Mistral Small 3 24B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkArena Hard | Score87.6% | Rank05 | Participants26 | Percentile84.0% | EvidenceC | Evaluated |
| BenchmarkWild Bench | Score52.2% | Rank06 | Participants8 | Percentile28.6% | EvidenceC | Evaluated |
| BenchmarkMT-Bench | Score83.5% | Rank08 | Participants12 | Percentile36.4% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score84.8% | Rank37 | Participants66 | Percentile44.6% | EvidenceC | Evaluated |
| BenchmarkMATH | Score70.6% | Rank37 | Participants71 | Percentile48.6% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score82.9% | Rank47 | Participants67 | Percentile30.3% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score66.3% | Rank103 | Participants134 | Percentile23.3% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score45.3% | Rank197 | Participants239 | Percentile17.6% | EvidenceC | Evaluated |
Mistral Small 3 24B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryoverall | Rank272 | Rating / score1233.6 | Votes14,681 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank281 | Rating / score1274.2 | Votes14,681 | ObservationsN/A | Result date |
Mistral Small 3 24B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
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 24B Runtime Performance
Provider-specific output speed and catalog latency for Mistral Small 3 24B Instruct. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderMistral AI | Output Speed134 tok/s | Catalog Latency0.2 s | Max Input32K | Max Output32K | Updated |
| ProviderDeepInfra | Output Speed49 tok/s | Catalog Latency0.2 s | Max Input32K | Max Output32K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Mistral Small 3 24B Specifications
Technical details for the model's default version.
- Version
- Mistral Small 3 24B Instruct
- Released
- Jan 30, 2025
- Knowledge cutoff
- Oct 1, 2023
- Parameters
- 24B
- Context window
- 32K
- Max output
- 32K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Apache 2.0
Mistral Small 3 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 24B Base | Released | LLMBoardN/A | Parameters23.6B | ContextN/A | Max outputN/A | Open weightsNo | LicenseApache 2.0 |
| VersionMistral Small 3 24B Instruct | Released | LLMBoard6.7 | Parameters24B | Context32K | Max output32K | Open weightsNo | LicenseApache 2.0 |
Mistral Small 3 24B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Mistral Small 3 24B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Mistral Large 2
Mistral AI
MA
Mistral Small 3.1 24B
Mistral AI
MA
Codestral 22B
Mistral AI
MA
Mistral NeMo
Mistral AI
MA
Shieldstral 1.0
Mistral AI
MA
Pixtral 12B
Mistral AI
What is Mistral Small 3 24B?
Key information about Mistral Small 3 24B and its available data.
3 70B or Qwen 32B, and is an excellent open replacement for opaque proprietary models like GPT4o-mini. 3 70B instruct, while being more than 3x faster on the same hardware.
Data as of 2026-08-17.
FAQ
Common questions about Mistral Small 3 24B.
When was Mistral Small 3 24B released?
Mistral Small 3 24B's default version was released on Jan 30, 2025.
How much does Mistral Small 3 24B cost?
No official standard PAYG price is currently available for Mistral Small 3 24B.
Who created Mistral Small 3 24B?
Mistral Small 3 24B was created by Mistral AI.
What is the context window for Mistral Small 3 24B?
The default version has a 32K token context window.
Is Mistral Small 3 24B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Mistral Small 3 24B?
No provider offering is currently linked to the default version.
What models should I compare Mistral Small 3 24B with?
Nearby ranked alternatives include Qwen2.5 14B, GPT-4o-mini, Hermes 3 70B.