跳到正文
智迹闻AuraTracer

发布于

Muse Wonder Full

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 88.5 · 11项基准

推理求解 87.2

Terminal-Bench-Science · 0.371428571428571 比例

Artificial Analysis · 独立评测 · 0.1.0

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

HLE · 0.485 比例

Artificial Analysis · 独立评测 · Diamond

Muse Wonder Full (Max) · Artificial Analysis current published protocol; hle-diamond

CritPt · 0.565 比例

Artificial Analysis · 独立评测 · 2 Hard

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

工具与任务执行 94.2

GDPval-AA · 1857.09 分

Artificial Analysis · 独立评测 · 2.1

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

Terminal-Bench · 58.08%

Vals AI · 独立评测 · 4.0

Muse Wonder Full / Mini-SWE-agent · Current displayed evaluator row. Mini-SWE-agent. Scores are not pooled across harnesses; source methodology and repeat counts retained.

AutomationBench · 0.7133074973223975 比例

Artificial Analysis · 独立评测 · current published task suite

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

AA-Briefcase · 1729.32 分

Artificial Analysis · 独立评测 · 1.1

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

编程 80.4

FrontierCode · 0.377576262626263 比例

Artificial Analysis · 独立评测 · 2.0

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

Vals Code Migration · 62.79%

Vals AI · 独立评测 · 1.1

Muse Wonder Full / 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 91.0

GDP.pdf · 0.326 比例

Artificial Analysis · 独立评测 · current published task suite

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

AA-Omniscience · 0.4096666666666667 比例

Artificial Analysis · 独立评测 · 1.1

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

AA-Omniscience · 0.8243929983060418 比例

Artificial Analysis · 独立评测 · 1.1

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

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