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 12, 2026. Default version: Magistral Medium
LLMBoard score19.8Magistral Medium
Coverage80%6 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
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 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.
| Aider-Polyglot | 0.5 | 18 | 22 | 19.1% | C | |
| AIME 2024 | 0.7 | 36 | 53 | 32.7% | C | |
| LiveCodeBench | 0.5 | 44 | 73 | 40.3% | C | |
| Humanity's Last Exam | 0.1 | 83 | 93 | 10.9% | C | |
| AIME 2025 | 0.6 | 93 | 114 | 18.6% | C | |
| GPQA | 0.7 | 126 | 234 | 46.4% | C |
Magistral Medium Arena Results
Preference and agent-evaluation results for the default version.
| text style control | overall | 255 | 1304.0 | 11,677 | N/A | |
| text | overall | 264 | 1254.4 | 11,677 | N/A |
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 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Magistral Medium | 19.8 | 24B | N/A | N/A | No | Apache 2.0 |
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 2026-08-11.
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
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.