跳到正文
智迹闻AuraTracer

发布于

GLM-5.3-Flash

开始使用

API 接入

Zhipu AI API文档
目录部署标识:glm-5.3-flash。具体区域、权限与价格以服务商为准。

相关动态

订阅更新
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 54.6 · 16项基准

推理求解 61.0

GPQA Diamond · 0.912121212121212 比例

Artificial Analysis · 独立评测 · Diamond

GLM-5.3-Flash · Current AA standalone protocol. Status verified in aa-method-current.md section gpqa-diamond

Terminal-Bench-Science · 0.0476190476190476 比例

Artificial Analysis · 独立评测 · 0.1.0

GLM-5.3-Flash · Artificial Analysis current published protocol; terminal-bench-science

HLE · 0.182 比例

Artificial Analysis · 独立评测 · Diamond

GLM-5.3-Flash · Artificial Analysis current published protocol; hle-diamond

CritPt · 0.245 比例

Artificial Analysis · 独立评测 · 2 Hard

GLM-5.3-Flash · Artificial Analysis current published protocol; critpt-v2-hard

工具与任务执行 61.9

tau3-Banking · 0.472164948453608 比例

Artificial Analysis · 独立评测 · 1.0.1

GLM-5.3-Flash · Current AA standalone protocol. Status verified in aa-method-current.md section tau3-banking

GDPval-AA · 1649.37 分

Artificial Analysis · 独立评测 · 2.1

GLM-5.3-Flash · Artificial Analysis current published protocol; gdpval-aa-normalized

Terminal-Bench · 37.37%

Vals AI · 独立评测 · 4.0

GLM-5.3-Flash / Mini-SWE-agent · Current displayed evaluator row. Mini-SWE-agent. Scores are not pooled across harnesses; source methodology and repeat counts retained.

AutomationBench · 0.6036862782167782 比例

Artificial Analysis · 独立评测 · current published task suite

GLM-5.3-Flash · Artificial Analysis current published protocol; automationbench-aa

AA-Briefcase · 1450.94 分

Artificial Analysis · 独立评测 · 1.1

GLM-5.3-Flash · Artificial Analysis current published protocol; aa-briefcase

EnterpriseOps-Gym · 0.3321396598030439 比例

Artificial Analysis · 独立评测 · current published task suite

GLM-5.3-Flash · Artificial Analysis current published protocol; enterprise-ops-gym-aa

AA-AnalystAgent · 0.25 比例

Artificial Analysis · 独立评测 · current AA pass^5

GLM-5.3-Flash · Artificial Analysis current published protocol; aa-analyst-agent

编程 48.6

FrontierCode · 0.176070454545455 比例

Artificial Analysis · 独立评测 · 2.0

GLM-5.3-Flash · Artificial Analysis current published protocol; frontiercode-2-0

Vals Code Migration · 51.65%

Vals AI · 独立评测 · 1.1

GLM-5.3-Flash / 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 53.9

GDP.pdf · 0.154 比例

Artificial Analysis · 独立评测 · current published task suite

GLM-5.3-Flash · Artificial Analysis current published protocol; gdp-pdf

AA-Omniscience · 0.282 比例

Artificial Analysis · 独立评测 · 1.1

GLM-5.3-Flash · Artificial Analysis current published protocol; omniscience-accuracy

AA-Omniscience · 0.6165273909006499 比例

Artificial Analysis · 独立评测 · 1.1

GLM-5.3-Flash · Artificial Analysis current published protocol; omniscience-non-hallucination

多模态理解 33.3

Humanity Sixth Sense · 26.8 %

Scale AI · 独立评测 · current published task suite

GLM-5.3-Flash (max) · scale-hss-reviewed-method-20261029

查看原始成绩与计算数据

资料来源
  • 版本日期来源 · 版本资料 · 2026-10-29查阅
  • Vals AI · independent_evaluation · 2026-10-29查阅
  • Vals AI · independent_evaluation · 2026-10-29查阅
  • Scale AI · independent_evaluation · 2026-10-29查阅

模型资料来源 · 目录许可