Compare · ModelsLive · 2 picked · head to head
Llama 4 Scout vs Magistral Small 1.1
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Llama 4 Scout wins on 2/4 benchmarks
Llama 4 Scout wins 2 of 4 shared benchmarks. Leads in knowledge.
Category leads
reasoning·Magistral Small 1.1knowledge·Llama 4 Scoutmath·Magistral Small 1.1
Hype vs Reality
Attention vs performance
Llama 4 Scout
#289 by perf·#18 by attention
Magistral Small 1.1
#296 by perf·no signal
Best value
Llama 4 Scout
Llama 4 Scout
97.5 pts/$
$0.20/M
Magistral Small 1.1
n/a
no price
Vendor risk
Who is behind the model
Meta AI
$1.87T·Tier 1
U
Unknown
private · undisclosed
Head to head
4 benchmarks · 2 models
Llama 4 ScoutMagistral Small 1.1
ARC-AGI
Magistral Small 1.1 leads by +4.5
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Llama 4 Scout
0.5
Magistral Small 1.1
5.0
ARC-AGI-2
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Llama 4 Scout
0.0
Magistral Small 1.1
0.0
GPQA diamond
Llama 4 Scout leads by +4.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Llama 4 Scout
35.8
Magistral Small 1.1
31.2
OTIS Mock AIME 2024-2025
Magistral Small 1.1 leads by +22.2
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Llama 4 Scout
7.7
Magistral Small 1.1
29.9
Full benchmark table
| Benchmark | Llama 4 Scout | Magistral Small 1.1 |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 0.5 | 5.0 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 0.0 | 0.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 35.8 | 31.2 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 7.7 | 29.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.10 | $0.30 | 1.3M tokens (~655 books) | $1.50 | |
U Magistral Small 1.1 | — | — | — | — |