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.
发布日期
2026-09-02
参数规模
—
上下文长度
1.0M
支持模态
audio, image, pdf, text, video
能力雷达图
59
general
73
coding
94
reasoning
72
science
70
agents
70
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
Job Bench
64.9%自报
Agentic IF Index (Internal)
57.8%自报
AutomationBench
49.4%自报
Code
DeepSWE 1.1
75.4%自报
SWE Atlas - Codebase QnA
59.4%自报
General
GDPval-AA
1754.00 / 3000自报
Long Context
MRCR v2 (8-needle)
98.5%自报
MRCR v2 (8-needle, 512K-1M)
98.1%自报
Multimodal
OSWorld 2.0
66.9%自报
Reasoning
Terminal-Bench 2.1
88.8%自报
Search
DeepSearchQA
89.4%自报
AA 评测指数
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))93.8
Terminalbench V2 185.8
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 Banking52.4
Hle(Center for AI Safety + Scale AI (2025))49.1
LLM Stats 分类评分
(LLM Stats (zeroeval))Legal100
Finance100
Reasoning100
Agents100
General100
Long Context100
Search90
Multimodal70
Code70
Tool Calling70
Vision70
Productivity60
定价
输入价格免费
输出价格免费
混合价格(3:1)免费
缓存读取价格$0.15 / 1M tokens
速度
Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s
供应商价格排行
供应商价格排行
2 个供应商
最便宜: Meta Model API最贵: EmpirioLabs AI
供应商输入输出
1Meta Model API最便宜
$0
$0
2EmpirioLabs AI
$1.25
$4.25
比较该模型在不同 API 供应商之间的定价。