跳到正文
智迹闻AuraTracer

发布于

Quasar 438B

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 37.5 · 8项基准

推理求解 31.6

GPQA Diamond · 0.732323232323232 比例

Artificial Analysis · 独立评测 · Diamond

Quasar 438B (Max, Based on GLM-5.2) · Current AA standalone protocol. Status verified in aa-method-current.md section gpqa-diamond

HLE · 0.131 比例

Artificial Analysis · 独立评测 · Diamond

Quasar 438B (Max, Based on GLM-5.2) · Artificial Analysis current published protocol; hle-diamond

工具与任务执行 50.8

tau3-Banking · 0.28659793814433 比例

Artificial Analysis · 独立评测 · 1.0.1

Quasar 438B (Max, Based on GLM-5.2) · Current AA standalone protocol. Status verified in aa-method-current.md section tau3-banking

GDPval-AA · 1189.7 分

Artificial Analysis · 独立评测 · 2.1

Quasar 438B (Max, Based on GLM-5.2) · Artificial Analysis current published protocol; gdpval-aa-normalized

Terminal-Bench · 0.0101010101010101 比例

Artificial Analysis · 独立评测 · 4.0

Quasar 438B (Max, Based on GLM-5.2) · Artificial Analysis current published protocol; terminalbench-4-0

AutomationBench · 0.23864439593997933 比例

Artificial Analysis · 独立评测 · current published task suite

Quasar 438B (Max, Based on GLM-5.2) · Artificial Analysis current published protocol; automationbench-aa

AA-Briefcase · 1123.55 分

Artificial Analysis · 独立评测 · 1.1

Quasar 438B (Max, Based on GLM-5.2) · Artificial Analysis current published protocol; aa-briefcase

语言与信息处理 28.3

GDP.pdf · 0.054 比例

Artificial Analysis · 独立评测 · current published task suite

Quasar 438B (Max, Based on GLM-5.2) · Artificial Analysis current published protocol; gdp-pdf

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