Llama 3.2 Instruct 90B (Vision)

MetaLlama开源权重Llama 3.2 · 商用许可

描述

Llama 3.2 90B is a large multimodal language model optimized for visual recognition, image reasoning, and captioning tasks. It supports a context length of 128,000 tokens and is designed for deployment on edge and mobile devices, offering state-of-the-art performance in image understanding and generative tasks.

发布日期

2024-09-25

参数规模

90.0B

上下文长度

—

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	483	23.0	AA
通用能力榜	505	28.0	AA
多模态榜	105	43.0	LS
科学能力	536	23.0	AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

General

MMLU

86.0%自报

Math

MGSM

86.9%自报

MATH

68.0%自报

MathVista

57.3%自报

Multimodal

MMMU

60.3%自报

Reasoning

ChartQAMasry et al. (2022)

85.5%自报

GPQANYU + Cohere + Anthropic (2023)

46.7%自报

Vision

AI2D

92.3%自报

DocVQADocVQA (2020)

90.1%自报

VQAv2

78.1%自报

TextVQA

73.5%自报

InfographicsQA

56.8%自报

MMMU-Pro

45.2%自报

AA 评测指数

(Artificial Analysis)

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

67.1

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

62.9

Gpqa(NYU + Cohere + Anthropic (2023))

43.2

Livecodebench(UC Berkeley + MIT + Cornell (2024))

21.4

Intelligence Index(Artificial Analysis)

6.4

Aime(MAA (Mathematical Association of America))

5.0

Hle(Center for AI Safety + Scale AI (2025))

4.5

LLM Stats 分类评分

(LLM Stats (zeroeval))

Language

Legal

Finance

Image To Text

Math

Multimodal

Reasoning

General

Healthcare

Vision

Physics

Biology

Chemistry

定价

输入价格免费

输出价格免费

混合价格(3:1)免费

速度

Tokens/秒0.0

首Token延迟0.00s

首回答延迟0.00s

供应商价格排行

暂无提供商数据

外部链接

LLM Stats Artificial Analysis