跳到正文
智迹闻AuraTracer

发布于

Muse Wonder

开始使用

API 接入

CommandCode API文档
目录部署标识:meta/muse-wonder-1.0。具体区域、权限与价格以服务商为准。

Meta API文档
目录部署标识:muse-wonder-1.0。具体区域、权限与价格以服务商为准。

Cloudflare AI Gateway API文档
目录部署标识:meta/muse-wonder-1.0。具体区域、权限与价格以服务商为准。

Vercel AI Gateway API文档
目录部署标识:meta/muse-wonder-1.0。具体区域、权限与价格以服务商为准。

Eden AI API文档
目录部署标识:meta/muse-wonder-1.0。具体区域、权限与价格以服务商为准。

LLM Gateway API文档
目录部署标识:meta/muse-wonder-1.0。具体区域、权限与价格以服务商为准。

公开成绩与计算依据

综合参考分根据已公开的评测资料整理。查看发布日期依据

综合参考分 81.7 · 14项基准

推理求解 70.3

FrontierMath · 0.7073170731707317 比例

Epoch AI · 独立评测 · 2

muse-wonder-1.0_max · epoch-frontiermath-reviewed-method-20261029-task-version-2.1.0 · 2026-10-12公开

Terminal-Bench-Science · 0.257142857142857 比例

Artificial Analysis · 独立评测 · 0.1.0

Muse Wonder (Max) · Artificial Analysis current published protocol; terminal-bench-science

HLE · 37.3 %

Scale AI · 独立评测 · Diamond

muse-wonder-1.0 · scale-hle-reviewed-method-20261029

CritPt · 0.505 比例

Artificial Analysis · 独立评测 · 2 Hard

Muse Wonder (Max) · Artificial Analysis current published protocol; critpt-v2-hard

工具与任务执行 91.3

GDPval-AA · 1770.34 分

Artificial Analysis · 独立评测 · 2.1

Muse Wonder (Max) · Artificial Analysis current published protocol; gdpval-aa-normalized

Terminal-Bench · 0.52020202020202 比例

Artificial Analysis · 独立评测 · 4.0

Muse Wonder (Max) · Artificial Analysis current published protocol; terminalbench-4-0

AutomationBench · 0.6809455131207758 比例

Artificial Analysis · 独立评测 · current published task suite

Muse Wonder (Max) · Artificial Analysis current published protocol; automationbench-aa

AA-Briefcase · 1658.65 分

Artificial Analysis · 独立评测 · 1.1

Muse Wonder (Max) · Artificial Analysis current published protocol; aa-briefcase

编程 80.1

FrontierCode · 0.27875303030303 比例

Artificial Analysis · 独立评测 · 2.0

Muse Wonder (Max) · Artificial Analysis current published protocol; frontiercode-2-0

Vals Code Migration · 72.36%

Vals AI · 独立评测 · 1.1

Muse Wonder / Published Code Migration 1.1 sandbox · Current displayed evaluator row. Published Code Migration 1.1 sandbox. Scores are not pooled across harnesses; source methodology and repeat counts retained.

语言与信息处理 85.1

GDP.pdf · 0.306 比例

Artificial Analysis · 独立评测 · current published task suite

Muse Wonder (Max) · Artificial Analysis current published protocol; gdp-pdf

AA-Omniscience · 0.38033333333333336 比例

Artificial Analysis · 独立评测 · 1.1

Muse Wonder (Max) · Artificial Analysis current published protocol; omniscience-accuracy

AA-Omniscience · 0.7912856374394837 比例

Artificial Analysis · 独立评测 · 1.1

Muse Wonder (Max) · Artificial Analysis current published protocol; omniscience-non-hallucination

多模态理解 82.3

Humanity Sixth Sense · 43.7 %

Scale AI · 独立评测 · current published task suite

Muse Wonder 1.0 (max) · scale-hss-reviewed-method-20261029

MMMU-Pro · 0.838150289017341 比例

Artificial Analysis · 独立评测 · Standard 10

Muse Wonder (High) · Artificial Analysis current published protocol; mmmu-pro

查看原始成绩与计算数据

资料来源

模型资料来源 · 目录许可