跳轉到主要內容

Pixtral Large

Mistral開源權重Mistral Research License (MRL) for research; Mistral Commercial License for commercial use

描述

A 124B parameter multimodal model built on top of Mistral Large 2, featuring frontier-level image understanding capabilities. Excels at understanding documents, charts, and natural images while maintaining strong text-only performance. Features a 123B multimodal decoder and 1B parameter vision encoder with a 128K context window supporting up to 30 high-resolution images.

發布日期
2024-11-18
參數規模
124.0B
上下文長度
128K
支援模態
image, text

能力雷達圖

26
general
27
coding
19
reasoning
34
science
21
agents
90
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜419
21.0
AA
通用能力榜389
33.0
AA
多模態榜18
62.0
LS
科學能力404
33.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Communication

MM-MT-Bench0.74 / 100自報

General

MMMU64.0%自報

Image To Text

DocVQADocVQA (2020)93.3%自報
VQAv280.9%自報

Math

MathVista69.4%自報

Multimodal

AI2D93.8%自報
ChartQAMasry et al. (2022)88.1%自報

AA 評測指數

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
8.0
Math Index(Artificial Analysis)
2.3
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.7
Gpqa(NYU + Cohere + Anthropic (2023))
0.5
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.4
Ifbench(Google Research (2023))
0.3
Scicode(UIUC + Argonne National Lab (2024))
0.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.3
Lcr(Artificial Analysis)
0.1
Aime(MAA (Mathematical Association of America))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.0
Aime 25(MAA (Mathematical Association of America))
0.0

LLM Stats 分類評分

(LLM Stats (zeroeval))
Image To Text
90
Multimodal
80
Reasoning
80
General
80
Vision
80
Math
70
Communication
70
Healthcare
60

定價

輸入價格免費
輸出價格免費
混合價格(3:1)免費

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

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
1Mistral
$2
$6

比較該模型在不同 API 供應商之間的定價。

外部連結