跳轉到主要內容

Muse Spark 1.3 (max)

MetaProprietary

描述

Muse Spark 1.3 is Meta Superintelligence Labs' proprietary multimodal reasoning model for long-running agentic, multi-agent, and coding workflows. It improves on Muse Spark 1.2 in long-horizon collaboration, multitasking, instruction following, tool use, failure recovery, and concise coding execution. It supports a 1,048,576-token context window and is available through Muse Code and the Meta Model API. ZeroEval routes to the lower-cost contributor endpoint, where prompts and outputs may be used to improve Meta's products.

發布日期
2026-09-02
參數規模
上下文長度
1.0M
支援模態
audio, image, pdf, text, video

能力雷達圖

59
general
73
coding
94
reasoning
72
science
70
agents
70
multimodal

排行榜排名

領域#排名分數來源
智慧體能力模型榜1
72.0
LS
程式碼能力榜9
94.0
AA
通用能力榜6
94.0
AA
多模態榜40
58.0
LS
科學能力9
91.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Job Bench64.9%自報
Agentic IF Index (Internal)57.8%自報
AutomationBench49.4%自報

Code

DeepSWE 1.175.4%自報
SWE Atlas - Codebase QnA59.4%自報

General

GDPval-AA1754.00 / 3000自報

Long Context

MRCR v2 (8-needle)98.5%自報
MRCR v2 (8-needle, 512K-1M)98.1%自報

Multimodal

OSWorld 2.066.9%自報

Reasoning

Terminal-Bench 2.188.8%自報

Search

DeepSearchQA89.4%自報

AA 評測指數

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
93.8
Terminalbench V2 1
85.8
Lcr(Artificial Analysis)
79.0
Coding Index(Artificial Analysis)
76.3
Intelligence Index(Artificial Analysis)
62.1
Scicode(UIUC + Argonne National Lab (2024))
57.3
Tau Banking
52.4
Hle(Center for AI Safety + Scale AI (2025))
49.1

LLM Stats 分類評分

(LLM Stats (zeroeval))
Legal
100
Finance
100
Reasoning
100
Agents
100
General
100
Long Context
100
Search
90
Multimodal
70
Code
70
Tool Calling
70
Vision
70
Productivity
60

定價

輸入價格免費
輸出價格免費
混合價格(3:1)免費
快取讀取價格$0.15 / 1M tokens

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

2 個供應商

最便宜: Meta Model API最貴: EmpirioLabs AI
供應商輸入輸出
1Meta Model API最便宜
$0
$0
2EmpirioLabs AI
$1.25
$4.25

比較該模型在不同 API 供應商之間的定價。

外部連結