跳转到主要内容

Llama 4 Scout

MetaLlama开源权重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.

发布日期
2025-04-05
参数规模
109.0B
上下文长度
1.3M
支持模态
image, text

能力雷达图

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

排行榜排名

领域#排名分数来源
代码能力榜443
18.0
AA
通用能力榜383
33.0
AA
科学能力432
30.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)57.2%自报

Code

LiveCodeBench32.8%自报

Finance

MMLU79.6%自报
MMLU-Pro74.3%自报

General

MMMU69.4%自报
MBPP0.68 / 100自报

Image To Text

DocVQADocVQA (2020)94.4%自报

Language

TydiQA31.5%自报

Math

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

Multimodal

ChartQAMasry et al. (2022)88.8%自报

AA 评测指数

(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 分类评分

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

定价

输入价格$0.18 / 1M tokens
输出价格$0.66 / 1M tokens
混合价格(3:1)$0.3 / 1M tokens

速度

Tokens/秒129.9
首Token延迟0.61s
首回答延迟0.61s

供应商价格排行

供应商价格排行

5 个供应商

最便宜: Helicone最贵: Meta
供应商输入输出
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

比较该模型在不同 API 供应商之间的定价。

外部链接