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

general

coding

reasoning

science

agents

multimodal

排行榜排名

領域	#排名	分數	來源
程式碼能力榜	533	17.0	AA
通用能力榜	453	31.0	AA
多模態榜	88	49.0	LS
科學能力	488	28.0	AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

General

MMLU

79.6%自報

Language

MMLU-Pro

74.3%自報

TydiQA

31.5%自報

Math

MGSM

90.6%自報

MathVista

70.7%自報

MATH

50.3%自報

Multimodal

MMMU

69.4%自報

Reasoning

ChartQAMasry et al. (2022)

88.8%自報

MBPP

0.68 / 100自報

GPQANYU + Cohere + Anthropic (2023)

57.2%自報

LiveCodeBench

32.8%自報

Vision

DocVQADocVQA (2020)

94.4%自報

AA 評測指數

(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 分類評分

(LLM Stats (zeroeval))

Image To Text

Language

Legal

Multimodal

Finance

Vision

Math

Reasoning

General

Healthcare

Physics

Biology

Chemistry

Code

定價

輸入價格$0.19 / 1M tokens

輸出價格$0.68 / 1M tokens

混合價格(3:1)$0.313 / 1M tokens

速度

Tokens/秒120.7

首Token延遲0.66s

首回答延遲0.66s

供應商價格排行

6 個供應商

最便宜: DeepInfra最貴: Meta

供應商輸入輸出

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

比較該模型在不同 API 供應商之間的定價。

外部連結

LLM Stats Artificial Analysis