跳轉到主要內容

Muse Wonder (Max)

MetaProprietary

描述

Muse Wonder is a proprietary reasoning model from Meta Superintelligence Labs, released on October 12, 2026 for personal and professional agents and long-running coding tasks. Active Memory retains relevant context across interactions, and Active Focus supports sustained task execution and error recovery. Muse Wonder accepts text, images, video, audio, and PDFs and produces text with a 1,048,576-token context window. It is available through the Meta Model API as muse-wonder-1.0 and in Muse Code.

發布日期
2026-10-12
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

52
general
60
coding
40
reasoning
57
science
50
agents
50
multimodal

排行榜排名

領域#排名分數來源
智慧體能力模型榜105
37.0
LS
程式碼能力榜32
91.0
AA
通用能力榜8
90.0
AA
多模態榜141
32.0
LS
科學能力18
85.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

MemoryBench85.6%自報
JobBench70.5%自報
Personal Superintelligence Index54.3%自報
Program Bench50.0%自報
FocusBench44.9%自報
AutomationBench-AA39.1%自報

Code

DeepSWE 1.178.8%自報
SWE-Marathon53.1%自報
Terminal-Bench 4.0-AA52.0%自報

Finance

Vals Finance Agent v256.6%自報

General

Artificial Analysis52.0%自報
GDP.pdf30.8%自報

Healthcare

HealthBench Professional60.5%自報

Knowledge

Harvey LAB-AA10.0%自報

Multimodal

OSWorld 2.1 (partial)72.6%自報
OSWorld 2.1 (strict)34.3%自報

AA 評測指數

(Artificial Analysis)
Lcr(Artificial Analysis)
80.7
Scicode(UIUC + Argonne National Lab (2024))
60.3
Intelligence Index(Artificial Analysis)
52.4
Terminalbench V4 0
52.0
Hle(Center for AI Safety + Scale AI (2025))
50.1

LLM Stats 分類評分

(LLM Stats (zeroeval))
Long Context
90
Productivity
70
Finance
60
Healthcare
60
Code
60
Knowledge
50
Multimodal
50
General
50
Agents
50
Tool Calling
50
Vision
50
Reasoning
40

定價

輸入價格$4 / 1M tokens
輸出價格$20 / 1M tokens
混合價格(3:1)$8 / 1M tokens
快取讀取價格$0.2 / 1M tokens

速度

Tokens/秒143.6
首Token延遲21.20s
首回答延遲35.12s

供應商價格排行

供應商價格排行

2 個供應商

最便宜: Meta最貴: Venice AI
供應商輸入輸出
1Meta主要
$4
$20
2Venice AI
$5
$25

比較該模型在不同 API 供應商之間的定價。

外部連結