跳到正文
智迹闻AuraTracer

发布于

Muse Spark Open

开始使用

API 接入

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

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

Prime Inference API文档
目录部署标识:meta/muse-spark-open。具体区域、权限与价格以服务商为准。

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

ai& API文档
目录部署标识:meta/muse-spark-open。具体区域、权限与价格以服务商为准。

OpenRouter API文档
目录部署标识:meta/muse-spark-open。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 48.6 · 17项基准

推理求解 44.5

FrontierMath · 0.3170731707317073 比例

Epoch AI · 独立评测 · 2

Muse-Spark-Open-816B-A42B_xhigh · epoch-frontiermath-reviewed-method-20261029-task-version-2.1.0 · 2026-10-15公开

GPQA Diamond · 0.88989898989899 比例

Artificial Analysis · 独立评测 · Diamond

Muse Spark Open (Xhigh) · Current AA standalone protocol. Status verified in aa-method-current.md section gpqa-diamond

Terminal-Bench-Science · 0.019047619047619 比例

Artificial Analysis · 独立评测 · 0.1.0

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; terminal-bench-science

HLE · 28 %

Scale AI · 独立评测 · Diamond

muse-spark-open · scale-hle-reviewed-method-20261029

CritPt · 0.295 比例

Artificial Analysis · 独立评测 · 2 Hard

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; critpt-v2-hard

工具与任务执行 58.8

GDPval-AA · 1401.12 分

Artificial Analysis · 独立评测 · 2.1

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; gdpval-aa-normalized

Terminal-Bench · 0.0808080808080808 比例

Artificial Analysis · 独立评测 · 4.0

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; terminalbench-4-0

AutomationBench · 0.4970811827313194 比例

Artificial Analysis · 独立评测 · current published task suite

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; automationbench-aa

AA-Briefcase · 1278.69 分

Artificial Analysis · 独立评测 · 1.1

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; aa-briefcase

编程 25.0

FrontierCode · 0.0760421717171717 比例

Artificial Analysis · 独立评测 · 2.0

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; frontiercode-2-0

Vals Code Migration · 26.89%

Vals AI · 独立评测 · 1.1

Muse Spark Open / 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 62.0

GDP.pdf · 0.186 比例

Artificial Analysis · 独立评测 · current published task suite

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; gdp-pdf

SimpleQA Verified · 0.566 比例

Epoch AI · 独立评测 · run 1.2.0

Muse-Spark-Open-816B-A42B_xhigh · epoch-simpleqa-reviewed-method-20261029-task-version-1.2.0 · 2026-10-15公开

MultiChallenge · 74.2 %

Scale AI · 独立评测 · current published task suite

Muse Spark Open · scale-multichallenge-reviewed-method-20261029

AA-Omniscience · 0.42033333333333334 比例

Artificial Analysis · 独立评测 · 1.1

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; omniscience-accuracy

AA-Omniscience · 0.7199539965497412 比例

Artificial Analysis · 独立评测 · 1.1

Muse Spark Open (Xhigh) · Artificial Analysis current published protocol; omniscience-non-hallucination

多模态理解 53.8

Humanity Sixth Sense · 29.6 %

Scale AI · 独立评测 · current published task suite

Muse Spark Open (max) · scale-hss-reviewed-method-20261029

MMMU-Pro · 0.809248554913295 比例

Artificial Analysis · 独立评测 · Standard 10

Muse Spark Open (Xhigh) · 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