跳轉到主要內容

Llama 4 Scout

MetaLlama開源權重Llama 4 Community License Agreement

描述

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.

發布日期
2025-04-05
參數規模
109.0B
上下文長度
1.3M
支援模態
image, text

能力雷達圖

29
general
17
coding
33
reasoning
33
science
28
agents
90
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜432
18.0
AA
通用能力榜371
33.0
AA
科學能力421
30.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)57.2%自報

Code

LiveCodeBench32.8%自報

Finance

MMLU79.6%自報
MMLU-Pro74.3%自報

General

MMMU69.4%自報
MBPP0.68 / 100自報

Image To Text

DocVQADocVQA (2020)94.4%自報

Language

TydiQA31.5%自報

Math

MGSM90.6%自報
MathVista70.7%自報
MATH50.3%自報

Multimodal

ChartQAMasry et al. (2022)88.8%自報

AA 評測指數

(Artificial Analysis)
Math Index(Artificial Analysis)
14.0
Intelligence Index(Artificial Analysis)
10.3
Coding Index(Artificial Analysis)
8.2
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.6
Ifbench(Google Research (2023))
0.4
Lcr(Artificial Analysis)
0.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.3
Aime(MAA (Mathematical Association of America))
0.3
Scicode(UIUC + Argonne National Lab (2024))
0.2
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.2
Aime 25(MAA (Mathematical Association of America))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.0
Terminalbench V2 1
0.0
Tau Banking
0.0
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

LLM Stats 分類評分

(LLM Stats (zeroeval))
Image To Text
90
Language
80
Legal
80
Multimodal
80
Finance
80
Vision
80
Math
70
Reasoning
70
General
70
Healthcare
70
Physics
60
Biology
60
Chemistry
60
Code
30

定價

輸入價格$0.18 / 1M tokens
輸出價格$0.66 / 1M tokens
混合價格(3:1)$0.3 / 1M tokens

速度

Tokens/秒120.3
首Token延遲0.61s
首回答延遲0.61s

供應商價格排行

供應商價格排行

5 個供應商

最便宜: Helicone最貴: Meta
供應商輸入輸出
1Helicone最便宜
$0.08
$0.3
2NanoGPT
$0.085
$0.46
3OpenRouter
$0.1
$0.3
4Kilo Gateway
$0.1
$0.3
5Meta主要
$0.18
$0.66

比較該模型在不同 API 供應商之間的定價。

外部連結