Llama 4 Scout
MetaLlamaOpen WeightLlama 4 Community License Agreement
Description
Llama 4 Scout is a natively multimodal model capable of processing both text and images. It features a 17 billion activated parameter (109B total) mixture-of-experts (MoE) architecture with 16 experts, supporting a wide range of multimodal tasks such as conversational interaction, image analysis, and code generation. The model includes a 10 million token context window.
Date de sortie
2025-04-05
Paramètres
109.0B
Longueur du contexte
1.3M
Modalités
image, text
Radar de capacités
28
general
17
coding
33
reasoning
35
science
28
agents
90
multimodal
Classements
| Domaine | #Rang | Score | Source |
|---|---|---|---|
| Classement codage | 533 | 17.0 | AA |
| Classement général | 453 | 31.0 | AA |
| Classement multimodal | 88 | 49.0 | LS |
| Science | 488 | 28.0 | AA |
Scores de benchmarks (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
79.6%Aut.
Language
MMLU-Pro
74.3%Aut.
TydiQA
31.5%Aut.
Math
MGSM
90.6%Aut.
MathVista
70.7%Aut.
MATH
50.3%Aut.
Multimodal
MMMU
69.4%Aut.
Reasoning
ChartQAMasry et al. (2022)
88.8%Aut.
MBPP
0.68 / 100Aut.
GPQANYU + Cohere + Anthropic (2023)
57.2%Aut.
LiveCodeBench
32.8%Aut.
Vision
DocVQADocVQA (2020)
94.4%Aut.
Indices d'évaluation AA
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))84.4
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))75.2
Gpqa(NYU + Cohere + Anthropic (2023))58.7
Ifbench(Google Research (2023))39.5
Livecodebench(UC Berkeley + MIT + Cornell (2024))29.9
Aime(MAA (Mathematical Association of America))28.3
Lcr(Artificial Analysis)27.7
Scicode(UIUC + Argonne National Lab (2024))21.3
Tau2(Sierra + U Toronto + Vector Institute (2025))15.5
Aime 25(MAA (Mathematical Association of America))14.0
Math Index(Artificial Analysis)14.0
Coding Index(Artificial Analysis)8.2
Intelligence Index(Artificial Analysis)8.1
Hle(Center for AI Safety + Scale AI (2025))3.8
Terminalbench V2 13.7
Tau Banking3.3
Terminalbench Hard(Stanford × Laude Institute (2026))1.5
Terminalbench V4 00.0
Scores par catégorie LLM Stats
(LLM Stats (zeroeval))Image To Text90
Language80
Legal80
Multimodal80
Finance80
Vision80
Math70
Reasoning70
General70
Healthcare70
Physics60
Biology60
Chemistry60
Code30
Tarification
Prix d'entrée$0.19 / 1M tokens
Prix de sortie$0.68 / 1M tokens
Prix mixte (3:1)$0.313 / 1M tokens
Vitesse
Tokens/sec120.7
Délai du premier token0.66s
Temps de réponse0.66s
Classement des Prix par Fournisseur
Classement des Prix par Fournisseur
6 fournisseurs
Moins cher: DeepInfraPlus cher: Meta
FournisseurEntréeSortie
1DeepInfraMoins cher
$0
$0
2Helicone
$0.08
$0.3
3NanoGPT
$0.085
$0.46
4OpenRouter
$0.1
$0.3
5Kilo Gateway
$0.1
$0.3
6MetaPRINCIPAL
$0.19
$0.68
Comparer les prix entre différents fournisseurs API pour ce modèle.