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

general

coding

reasoning

science

agents

multimodal

排行榜排名

领域	#排名	分数	来源
代码能力榜	533	17.0	AA
通用能力榜	453	31.0	AA
多模态榜	88	49.0	LS
科学能力	488	28.0	AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

General

MMLU

79.6%自报

Language

MMLU-Pro

74.3%自报

TydiQA

31.5%自报

Math

MGSM

90.6%自报

MathVista

70.7%自报

MATH

50.3%自报

Multimodal

MMMU

69.4%自报

Reasoning

ChartQAMasry et al. (2022)

88.8%自报

MBPP

0.68 / 100自报

GPQANYU + Cohere + Anthropic (2023)

57.2%自报

LiveCodeBench

32.8%自报

Vision

DocVQADocVQA (2020)

94.4%自报

AA 评测指数

(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 1

3.7

Tau Banking

3.3

Terminalbench Hard(Stanford × Laude Institute (2026))

1.5

Terminalbench V4 0

0.0

LLM Stats 分类评分

(LLM Stats (zeroeval))

Image To Text

Language

Legal

Multimodal

Finance

Vision

Math

Reasoning

General

Healthcare

Physics

Biology

Chemistry

Code

定价

输入价格$0.19 / 1M tokens

输出价格$0.68 / 1M tokens

混合价格(3:1)$0.313 / 1M tokens

速度

Tokens/秒127.0

首Token延迟0.66s

首回答延迟0.66s

供应商价格排行

6 个供应商

最便宜: DeepInfra最贵: Meta

供应商输入输出

1DeepInfra最便宜

2Helicone

$0.08

$0.3

3NanoGPT

$0.085

$0.46

4OpenRouter

$0.1

$0.3

5Kilo Gateway

$0.1

$0.3

6Meta主要

$0.19

$0.68

比较该模型在不同 API 供应商之间的定价。

外部链接

LLM Stats Artificial Analysis