Llama 4 Scout vs Magistral Medium
Magistral Medium leads the LLM Stats Score 13.1 to 7.8.
Meta · Mistral AI · Updated for 2026
Which is better?
Magistral Medium leads the overall LLM Stats Score 13.1 to 7.8, ranking #250 overall.
In the 2 individual benchmarks reported for both models, Magistral Medium wins 2; this is a narrower head-to-head signal than the composite indexes.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Llama 4 Scout
- you want predictable pricing at $0.08/M input and $0.30/M output
Choose Magistral Medium
- overall performance matters — it scores 13.1 and ranks #250 on LLM Stats
- your work emphasizes reasoning — it leads those capability indexes
- you value its reported benchmark strengths — it wins 2 of 2 exact shared results
- you want the most recent training data — it shipped Jun 2025
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
12 reported for Llama 4 Scout · 6 for Magistral Medium
Llama 4 Scout outperforms in 0 benchmarks, while Magistral Medium is better at 2 benchmarks (GPQA, LiveCodeBench).
Magistral Medium significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Model Size
Parameter count comparison
Llama 4 Scout has 85.0B more parameters than Magistral Medium, making it 354.2% larger.
Context Window
Maximum input and output token capacity
Only Llama 4 Scout specifies input context (10,000,000 tokens). Only Llama 4 Scout specifies output context (10,000,000 tokens).
Input capabilities
Documented input modalities across available providers
Both Llama 4 Scout and Magistral Medium support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
Llama 4 Scout
Magistral Medium
License
Usage and distribution terms
Llama 4 Scout is licensed under Llama 4 Community License Agreement, while Magistral Medium uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
Llama 4 Community License Agreement
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
Llama 4 Scout was released on 2025-04-05, while Magistral Medium was released on 2025-06-10.
Magistral Medium is 2 months newer than Llama 4 Scout.
Apr 5, 2025
1.5 years ago
Jun 10, 2025
1.3 years ago
2mo newerKnowledge Cutoff
When training data ends
Magistral Medium has a documented knowledge cutoff of 2025-06-01, while Llama 4 Scout's cutoff date is not specified.
We can confirm Magistral Medium's training data extends to 2025-06-01, but cannot make a direct comparison without Llama 4 Scout's cutoff date.
—
Jun 2025
Outputs Comparison
Judge for yourself.
Run your own prompts against Llama 4 Scout and Magistral Medium side-by-side, then vote on the output you prefer.
FAQ
Common questions about Llama 4 Scout vs Magistral Medium.