Mistral AI model product
Magistral Medium
Trained solely with reinforcement learning on top of Mistral Medium 3, Magistral Medium is a reasoning model that achieves strong performance on complex math and code tasks without relying on distillation from existing reasoning models.
Updated Aug 17, 2026. Default version: Magistral Medium
LLMBoard Score18.8Magistral Medium
Coverage80%6 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Magistral Medium Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Magistral Medium Benchmark Results
Benchmark scores for Magistral Medium.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAider-Polyglot | Score47.1% | Rank18 | Participants22 | Percentile19.1% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score73.6% | Rank36 | Participants53 | Percentile32.7% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score50.3% | Rank46 | Participants75 | Percentile39.2% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score9.0% | Rank89 | Participants99 | Percentile10.2% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score64.9% | Rank93 | Participants115 | Percentile19.3% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score70.8% | Rank131 | Participants239 | Percentile45.4% | EvidenceC | Evaluated |
Magistral Medium Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryoverall | Rank258 | Rating / score1304.0 | Votes11,675 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank267 | Rating / score1254.3 | Votes11,675 | ObservationsN/A | Result date |
Magistral Medium 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.
Magistral Medium Runtime Performance
Provider-specific output speed and catalog latency for Magistral Medium. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo 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 Medium Specifications
Technical details for the model's default version.
- Version
- Magistral Medium
- Released
- Jun 10, 2025
- Knowledge cutoff
- Jun 1, 2025
- Parameters
- 24B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Apache 2.0
Magistral Medium 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 Medium | Released | LLMBoard18.8 | Parameters24B | ContextN/A | Max outputN/A | Open weightsNo | LicenseApache 2.0 |
Magistral Medium vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Magistral Medium
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Magistral Small
Mistral AI
MA
Min istral 3
Mistral AI
MA
Pixtral Large
Mistral AI
MA
Devstral Small 1.1
Mistral AI
MA
Mistral Small 3.2 24B
Mistral AI
MA
Mistral Large 3
Mistral AI
What is Magistral Medium?
Key information about Magistral Medium and its available data.
Trained solely with reinforcement learning on top of Mistral Medium 3, Magistral Medium is a reasoning model that achieves strong performance on complex math and code tasks without relying on distillation from existing reasoning models.
The training uses an RLVR framework with modifications to GRPO, enabling improved reasoning ability and multilingual consistency.
Data as of 2026-08-17.
FAQ
Common questions about Magistral Medium.
When was Magistral Medium released?
Magistral Medium's default version was released on Jun 10, 2025.
How much does Magistral Medium cost?
No official standard PAYG price is currently available for Magistral Medium.
Who created Magistral Medium?
Magistral Medium was created by Mistral AI.
What is the context window for Magistral Medium?
A context window is not available for the default version.
Is Magistral Medium open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Magistral Medium?
No provider offering is currently linked to the default version.
What models should I compare Magistral Medium with?
Nearby ranked alternatives include Min istral 3, Gemini 1.5 Pro, Magistral Small.