跳到正文
智迹闻AuraTracer

发布于

Tencent Hy4

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 75.8 · 9项基准

推理求解 76.5

Terminal-Bench-Science · 0.128571428571429 比例

Artificial Analysis · 独立评测 · 0.1.0

Tencent Hy4 · Artificial Analysis current published protocol; terminal-bench-science

HLE · 0.327 比例

Artificial Analysis · 独立评测 · Diamond

Tencent Hy4 · Artificial Analysis current published protocol; hle-diamond

CritPt · 0.39 比例

Artificial Analysis · 独立评测 · 2 Hard

Tencent Hy4 · Artificial Analysis current published protocol; critpt-v2-hard

工具与任务执行 79.9

Terminal-Bench · 0.373737373737374 比例

Artificial Analysis · 独立评测 · 4.0

Tencent Hy4 · Artificial Analysis current published protocol; terminalbench-4-0

AutomationBench · 0.6561018180201071 比例

Artificial Analysis · 独立评测 · current published task suite

Tencent Hy4 · Artificial Analysis current published protocol; automationbench-aa

AA-Briefcase · 1446.69 分

Artificial Analysis · 独立评测 · 1.1

Tencent Hy4 · Artificial Analysis current published protocol; aa-briefcase

编程 81.6

FrontierCode · 0.31447601010101 比例

Artificial Analysis · 独立评测 · 2.0

Tencent Hy4 · Artificial Analysis current published protocol; frontiercode-2-0

语言与信息处理 63.9

GDP.pdf · 0.216 比例

Artificial Analysis · 独立评测 · current published task suite

Tencent Hy4 · Artificial Analysis current published protocol; gdp-pdf

AA-Omniscience · 0.49966666666666665 比例

Artificial Analysis · 独立评测 · 1.1

Tencent Hy4 · Artificial Analysis current published protocol; omniscience-accuracy

AA-Omniscience · 0.10926049300466356 比例

Artificial Analysis · 独立评测 · 1.1

Tencent Hy4 · 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