跳转到主要内容

Muse Spark Open (Xhigh)

Meta开源权重Muse Model License · 商用许可

描述

Muse Spark Open is Meta Superintelligence Labs' open-weight natively multimodal Mixture-of-Experts model (816B total / 42B active parameters) with a 1,048,576-token context window. The HF model card specifies text, image, video, and audio inputs and text output. It supports configurable reasoning_effort (low/medium/high/xhigh; default xhigh) and is positioned for coding and agentic workflows. Weights are released under the Muse Model License with limited commercial terms and are available on Hugging Face as meta-models/Muse-Spark-Open-816B-A42B (BF16) and an NVFP4 sibling. Hosted inference is offered by third-party providers including Together AI, Fireworks AI, Groq, Modal, Nebius, Baseten, and OpenRouter (slug meta/muse-spark-open).

发布日期
2026-10-15
参数规模
816.0B
上下文长度
1.0M
支持模态
audio, image, pdf, text, video

能力雷达图

40
general
58
coding
89
reasoning
69
science
80
agents
70
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜81
44.0
LS
代码能力榜44
88.0
AA
通用能力榜77
66.0
AA
多模态榜23
62.0
LS
推理能力44
74.0
LB
科学能力26
83.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Toolathlon-Verified72.8%自报
Job Bench61.8%自报

Code

DeepSWE 1.160.0%自报
SWE Atlas - Codebase QnA58.0%自报

General

GDPval-AA1401.00 / 3000自报
Artificial Analysis39.0%自报

Knowledge

AA-Omniscience Index25.00 / 200自报

Multimodal

OSWorld-Verified80.4%自报

Reasoning

MCP Atlas89.2%自报
GPQANYU + Cohere + Anthropic (2023)89.0%自报
Terminal-Bench 2.176.4%自报
Humanity's Last Exam (with tools)61.0%自报
SciCode58.5%自报

Vision

BabyVision80.2%自报
SimpleVQA0.74 / 100自报
ZEROBench0.50 / 100自报
WorldVQA49.4%自报

AA 评测指数

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
89.0
Lcr(Artificial Analysis)
78.3
Terminalbench V2 1
76.4
Scicode(UIUC + Argonne National Lab (2024))
58.4
Hle(Center for AI Safety + Scale AI (2025))
43.9
Intelligence Index(Artificial Analysis)
38.9
Terminalbench V4 0
8.1

LLM Stats 分类评分

(LLM Stats (zeroeval))
Legal
100
Finance
100
Agents
100
Reasoning
100
General
85
Knowledge
25
Science
25
Tool Calling
80
Image To Text
70
Multimodal
70
Physics
70
Biology
70
Chemistry
70
Code
70
Vision
70
Math
60
Productivity
60

定价

输入价格$1.25 / 1M tokens
输出价格$4.25 / 1M tokens
混合价格(3:1)$2 / 1M tokens
缓存读取价格$0.15 / 1M tokens

速度

Tokens/秒213.4
首Token延迟0.58s
首回答延迟9.96s

供应商价格排行

供应商价格排行

12 个供应商

最便宜: Together最贵: Venice AI
供应商输入输出
1Together最便宜
$0
$0
2Meta主要
$1.25
$4.25
3NanoGPT
$1.25
$4.25
4OpenRouter
$1.25
$4.25
5Kilo Gateway
$1.25
$4.25
6Cloudflare AI Gateway
$1.25
$4.25
7Ollama Cloud
$1.25
$4.25
8Requesty
$1.25
$4.25
9Vercel AI Gateway
$1.25
$4.25
10Merge Gateway
$1.25
$4.25
11Prime Inference
$1.25
$4.25
12Venice AI
$1.5625
$5.3125

比较该模型在不同 API 供应商之间的定价。

外部链接