跳轉到主要內容

Llama 3.2 Instruct 11B (Vision)

MetaLlama開源權重Llama 3.2 Community License

描述

Llama 3.2 11B Vision Instruct is an instruction-tuned multimodal large language model optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. It accepts text and images as input and generates text as output.

發布日期
2024-09-25
參數規模
10.6B
上下文長度
支援模態
image, text

能力雷達圖

16
general
11
coding
13
reasoning
15
science
12
agents
90
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜486
11.0
AA
通用能力榜507
19.0
AA
多模態榜30
55.0
LS
科學能力526
14.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)32.8%自報

Finance

MMLU73.0%自報

General

MMMU50.7%自報
MMMU-Pro33.0%自報

Image To Text

DocVQADocVQA (2020)88.4%自報
VQAv2 (test)75.2%自報

Math

MGSM68.9%自報
MATH51.9%自報
MathVista51.5%自報

Multimodal

AI2D91.1%自報
ChartQAMasry et al. (2022)83.4%自報

AA 評測指數

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
3.0
Math Index(Artificial Analysis)
1.7
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.5
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.5
Ifbench(Google Research (2023))
0.3
Gpqa(NYU + Cohere + Anthropic (2023))
0.2
Lcr(Artificial Analysis)
0.2
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.1
Scicode(UIUC + Argonne National Lab (2024))
0.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.1
Aime(MAA (Mathematical Association of America))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.1
Aime 25(MAA (Mathematical Association of America))
0.0
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

LLM Stats 分類評分

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

定價

輸入價格$0.345 / 1M tokens
輸出價格$0.345 / 1M tokens
混合價格(3:1)$0.345 / 1M tokens

速度

Tokens/秒17.4
首Token延遲0.68s
首回答延遲0.68s

供應商價格排行

供應商價格排行

1 個供應商

供應商輸入輸出
1Meta主要
$0.345
$0.345

比較該模型在不同 API 供應商之間的定價。

外部連結