跳转到主要内容

Muse Spark

MetaProprietary

描述

Muse Spark is the first model in the Muse family developed by Meta Superintelligence Labs. It is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration. It features a Contemplating mode that orchestrates multiple agents reasoning in parallel. It demonstrates competitive performance in multimodal perception, reasoning, health, and agentic tasks, with Contemplating mode achieving 58% on Humanity's Last Exam and 38% on FrontierScience Research.

发布日期
2026-04-08
参数规模
—
上下文长度
—
支持模态
—

能力雷达图

70
general
70
coding
60
reasoning
77
science估算
80
agents
70
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

领域#排名分数来源
多模态榜22
63.0
LS

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Communication

Tau2 Telecom91.5%自报

Healthcare

MedXpertQA78.4%自报
HealthBench Hard42.8%自报

Reasoning

GPQANYU + Cohere + Anthropic (2023)89.5%自报
CharXiv-R86.4%自报
IPhO 202582.6%自报
LiveCodeBench Pro0.80 / 3000自报
SWE-Bench Verified77.4%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)59.0%自报
Humanity's Last Exam58.4%自报
SWE-Bench ProPrinceton NLP (2024)52.4%自报
ARC-AGI v242.5%自报
FrontierScience Research38.3%自报

Search

DeepSearchQA74.8%自报

Vision

ScreenSpot Pro84.1%自报
MMMU-Pro80.4%自报
SimpleVQA0.71 / 100自报
ERQA64.7%自报
ZEROBench0.33 / 100自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Physics
90
Biology
90
Chemistry
90
Communication
90
Frontend Development
80
Grounding
80
Tool Calling
80
Image To Text
70
Multimodal
70
Reasoning
70
Search
70
General
70
Code
70
Vision
70
Math
60
Spatial Reasoning
60
Healthcare
60
Agents
60
Science
40

定价

暂无定价数据

速度

暂无速度数据

供应商价格排行

暂无提供商数据

外部链接