跳转到主要内容

Llama 4 Maverick

MetaLlama开源权重Llama 4 Community License Agreement

描述

Llama 4 Maverick is a natively multimodal model capable of processing both text and images. It features a 17 billion active parameter mixture-of-experts (MoE) architecture with 128 experts, supporting a wide range of multimodal tasks such as conversational interaction, image analysis, and code generation. The model includes a 1 million token context window.

发布日期
2025-04-05
参数规模
400.0B
上下文长度
1.0M
支持模态
image, text

能力雷达图

33
general
26
coding
39
reasoning
43
science
35
agents
90
multimodal

排行榜排名

领域#排名分数来源
代码能力榜331
31.0
AA
通用能力榜311
39.0
AA
科学能力305
43.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)69.8%自报

Code

LiveCodeBench43.4%自报

Finance

MMLU85.5%自报
MMLU-Pro80.5%自报

General

MBPP0.78 / 100自报
MMMU73.4%自报
MMMU-Pro59.6%自报

Image To Text

DocVQADocVQA (2020)94.4%自报

Language

TydiQA31.7%自报

Math

MGSM92.3%自报
MathVista73.7%自报
MATH61.2%自报

Multimodal

ChartQAMasry et al. (2022)90.0%自报

AA 评测指数

(Artificial Analysis)
Math Index(Artificial Analysis)
19.3
Coding Index(Artificial Analysis)
16.3
Intelligence Index(Artificial Analysis)
14.5
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.7
Lcr(Artificial Analysis)
0.5
Ifbench(Google Research (2023))
0.4
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.4
Aime(MAA (Mathematical Association of America))
0.4
Scicode(UIUC + Argonne National Lab (2024))
0.3
Aime 25(MAA (Mathematical Association of America))
0.2
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.2
Terminalbench V2 1
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.0
Tau Banking
0.0

LLM Stats 分类评分

(LLM Stats (zeroeval))
Image To Text
90
Language
80
Legal
80
Math
80
Multimodal
80
Finance
80
General
80
Healthcare
80
Vision
80
Physics
70
Reasoning
70
Biology
70
Chemistry
70
Code
40

定价

输入价格$0.27 / 1M tokens
输出价格$0.85 / 1M tokens
混合价格(3:1)$0.415 / 1M tokens

速度

Tokens/秒130.2
首Token延迟0.63s
首回答延迟0.63s

供应商价格排行

供应商价格排行

7 个供应商

最便宜: NanoGPT最贵: Neon
供应商输入输出
1NanoGPT最便宜
$0.15
$0.6
2Helicone
$0.15
$0.6
3OpenRouter
$0.2
$0.696
4Kilo Gateway
$0.2
$0.696
5DigitalOcean
$0.2
$0.696
6Meta主要
$0.27
$0.85
7Neon
$0.5
$1.5

比较该模型在不同 API 供应商之间的定价。

外部链接