Muse Wonder Full

Meta·4 个数据来源·更新于 2026-11-10

上下文窗口1MArtificial Analysis

评测表现

只在同一来源、同一口径下比较。切换来源可查看不同测试结果。

4 个评测来源

当前配置:各基准设置见下表

采集于 2026-11-10查看原始页面

综合分数和同榜图表来自 LLM Stats 榜单(采集于 2026-11-10);下方逐项成绩来自模型页。榜单出处

LLM Stats · LLM Stats Score
52.8原榜第 12 名

同榜模型表现

LLM Stats Score · 同一来源与榜单口径,分数越高越好

7 个配置
所选配置其他配置
查看完整对比数据
模型与配置LLM Stats Score每任务成本
Gemini 4 Argon53.8未公布
GPT-6.1 Sol53.1未公布
Claude Opus 553未公布
Muse Wonder Full · 当前模型52.8未公布
Claude Fable 552.4未公布
GPT-5.6 Sol52.4未公布
Muse Wonder Full52.2未公布

不同来源的分数不能直接相加或横向比较;评测任务成本不是 API Token 单价。

逐项基准成绩

16 项已收录成绩 · 保留原始单位和测试条件

Artificial Analysis厂商自报 · 越高越好
56%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Artificial Analysis Intelligence Index v4.3, independently evaluated by Artificial Analysis and reproduced in Meta's model card. Reported on a 0-100 scale, stored as a fraction.

成绩出处
AutomationBench-AA厂商自报 · 越高越好
45.4%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Artificial Analysis strict pass@1; every deterministic end-state assertion must pass. Reported on a 0-100 scale, stored as a fraction.

成绩出处
DeepSWE 1.1厂商自报 · 越高越好
79%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Datacurve third-party pass@1 results; 113 tasks across 91 repositories and five languages, graded with functional and regression tests. Reported on a 0-100 scale, stored as a fraction.

成绩出处
FocusBench厂商自报 · 越高越好
54.2%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Internal personal agent evaluation across housing, travel, IT, and finance; persistence through blockers and adaptation across interactions and changing environments. Reported on a 0-100 scale, stored as a fraction. Score from the research blog chart; methodology: https://research.meta.ai/static/muse-wonder-model-card.

成绩出处
GDP.pdf厂商自报 · 越高越好
33.2%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Professional tasks grounded in supplied PDF material; score reported by Surge. Reported on a 0-100 scale, stored as a fraction.

成绩出处
Harvey LAB-AA厂商自报 · 越高越好
13.1%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Artificial Analysis result, version 1.1; share of legal deliverables meeting every criterion and passing hallucination checks. Reported on a 0-100 scale, stored as a fraction.

成绩出处
HealthBench Professional厂商自报 · 越高越好
62.3%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. 525 professional health questions, no tools, GPT-5.4 rubric grader; length-normalized weighted rubric score in a common internal framework. Reported on a 0-100 scale, stored as a fraction.

成绩出处
JobBench厂商自报 · 越高越好
75.3%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. 65 professional tasks across 35 occupations; mean task-specific rubric reward. Reported on a 0-100 scale, stored as a fraction.

成绩出处
MemoryBench厂商自报 · 越高越好
85.5%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Internal recall evaluation over 64K-100K-token conversations containing distractors, conflicting facts, and later updates; LLM judge with weighted question-specific rubrics. Reported on a 0-100 scale, stored as a fraction.

成绩出处
OSWorld 2.1 (partial)厂商自报 · 越高越好
78.4%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. 108 desktop workflows in a common internal framework with official environments and graders; mean per-task partial reward. Reported on a 0-100 scale, stored as a fraction.

成绩出处
OSWorld 2.1 (strict)厂商自报 · 越高越好
39.4%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. 108 desktop workflows in a common internal framework with official environments and graders; strict binary completion, separate from partial reward. Reported on a 0-100 scale, stored as a fraction.

成绩出处
Personal Superintelligence Index厂商自报 · 越高越好
59.1%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Internal composite of Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT, and DRACO. Reported on a 0-100 scale, stored as a fraction.

成绩出处
Program Bench厂商自报 · 越高越好
59%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. All models use mini-swe-agent; share of rollouts passing at least 95% of hidden behavioral tests; internet disabled after setup. Reported on a 0-100 scale, stored as a fraction.

成绩出处
SWE-Marathon厂商自报 · 越高越好
57.5%

Meta Muse Wonder model card, October 12, 2026; xhigh reasoning effort. Abundant AI pass@1 results on long-running software projects. External results retain their reporting harnesses; not a controlled common-harness comparison. Reported on a 0-100 scale, stored as a fraction.

成绩出处
Terminal-Bench 4.0-AA厂商自报 · 越高越好
57.1%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Artificial Analysis reported accuracy on terminal tasks with executable final-container-state verifiers. Reported on a 0-100 scale, stored as a fraction.

成绩出处
Vals Finance Agent v2厂商自报 · 越高越好
59.1%

Meta Muse Wonder model card, October 12, 2026; max reasoning effort. Vals AI private-test-set accuracy on financial analyst research tasks. Reported on a 0-100 scale, stored as a fraction.

成绩出处

技术规格

只展示有可靠来源的资料;优先采用厂商官网与官方模型仓库。

发布日期
2026-10-12LLM Stats
上下文窗口
1M TokenArtificial Analysis
开放权重
否Artificial Analysis
推理模式
支持Artificial Analysis
许可证
ProprietaryLLM Stats

价格与用量

美元 / 百万 Token。不同服务商或测试配置的报价分别列出。

暂无可核验的 API 报价。

每个数字,都有出处

同名模型通过开发机构和明确版本关联。预览版、日期版本和不同规模模型分别建档。

Artificial Analysis

公开评测数据;保留来源原始口径

2 条记录最近采集 2026-11-10

LLM Stats

公开模型页与公开榜单;自报成绩单独标识

4 条记录最近采集 2026-11-10

BenchLM

公开评测数据;保留来源原始口径

1 条记录最近采集 2026-11-10

Arena

Arena 官方公开数据集 · CC BY 4.0

2 条记录最近采集 2026-11-10
查看全部配置与采集记录
来源 / 配置采集时间原始数据
Artificial AnalysisMuse Wonder Full (max)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisMuse Wonder Full (Max)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
LLM StatsMuse Wonder Full2026-11-10T14:08:28Z查看来源
LLM StatsMuse Wonder Full2026-11-10T14:08:28Z查看来源
LLM StatsMuse Wonder FullSHA-256 94901c8846512509…2026-11-10T13:52:03Z查看来源
LLM StatsMuse Wonder FullSHA-256 1d7e56ceffc0d84a…2026-11-10T13:52:04Z查看来源
BenchLMMuse Wonder Full2026-11-10查看来源
ArenaMuse Wonder Full (Max)2026-11-10T14:07:52Z查看来源
ArenaMuse Wonder Full (Max)2026-11-10T14:07:52Z查看来源
继续浏览模型排行榜