跳到正文
智迹闻AuraTracer

发布于

JT-4.1 Flash 236B A21B

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 43.4 · 7项基准

推理求解 52.5

GPQA Diamond · 0.845454545454545 比例

Artificial Analysis · 独立评测 · Diamond

JT-4.1 Flash 236B A21B (Non-reasoning) · Current AA standalone protocol. Status verified in aa-method-current.md section gpqa-diamond

工具与任务执行 53.5

GDPval-AA · 1335.19 分

Artificial Analysis · 独立评测 · 2.1

JT-4.1 Flash 236B A21B (Reasoning) · Artificial Analysis current published protocol; gdpval-aa-normalized

Terminal-Bench · 0.0303030303030303 比例

Artificial Analysis · 独立评测 · 4.0

JT-4.1 Flash 236B A21B (Reasoning) · Artificial Analysis current published protocol; terminalbench-4-0

AutomationBench · 0.4647120946439391 比例

Artificial Analysis · 独立评测 · current published task suite

JT-4.1 Flash 236B A21B (Reasoning) · Artificial Analysis current published protocol; automationbench-aa

AA-Briefcase · 1092.44 分

Artificial Analysis · 独立评测 · 1.1

JT-4.1 Flash 236B A21B (Reasoning) · Artificial Analysis current published protocol; aa-briefcase

语言与信息处理 38.2

GDP.pdf · 0.086 比例

Artificial Analysis · 独立评测 · current published task suite

JT-4.1 Flash 236B A21B (Reasoning) · Artificial Analysis current published protocol; gdp-pdf

多模态理解 5.9

MMMU-Pro · 0.641040462427746 比例

Artificial Analysis · 独立评测 · Standard 10

JT-4.1 Flash 236B A21B (Non-reasoning) · 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