Qwen3.8 Max (0902)
开始使用
API 接入
Vercel AI Gateway API文档
目录部署标识：alibaba/qwen3.8-max-0902。具体区域、权限与价格以服务商为准。
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 71.6 · 18项基准
推理求解 72.1
GPQA Diamond · 0.928282828282828 比例
Artificial Analysis · 独立评测 · Diamond
Qwen3.8 Max (0902) · Current AA standalone protocol. Status verified in aa-method-current.md section gpqa-diamond
Terminal-Bench-Science · 0.119047619047619 比例
Artificial Analysis · 独立评测 · 0.1.0
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; terminal-bench-science
HLE · 0.24 比例
Artificial Analysis · 独立评测 · Diamond
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; hle-diamond
CritPt · 0.295 比例
Artificial Analysis · 独立评测 · 2 Hard
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; critpt-v2-hard
工具与任务执行 82.4
APEX-Agents · 0.424041297935103 比例
Artificial Analysis · 独立评测 · current published task suite
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; apex-agents-aa
tau3-Banking · 0.478350515463918 比例
Artificial Analysis · 独立评测 · 1.0.1
Qwen3.8 Max (0902) · Current AA standalone protocol. Status verified in aa-method-current.md section tau3-banking
GDPval-AA · 1673.9 分
Artificial Analysis · 独立评测 · 2.1
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; gdpval-aa-normalized
Terminal-Bench · 38.89%
Vals AI · 独立评测 · 4.0
Qwen3.8 Max (0902) / Mini-SWE-agent · Current displayed evaluator row. Mini-SWE-agent. Scores are not pooled across harnesses; source methodology and repeat counts retained.
AutomationBench · 0.561905381087678 比例
Artificial Analysis · 独立评测 · current published task suite
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; automationbench-aa
AA-Briefcase · 1606.14 分
Artificial Analysis · 独立评测 · 1.1
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; aa-briefcase
EnterpriseOps-Gym · 0.4762757385854969 比例
Artificial Analysis · 独立评测 · current published task suite
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; enterprise-ops-gym-aa
AA-AnalystAgent · 0.45 比例
Artificial Analysis · 独立评测 · current AA pass^5
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; aa-analyst-agent
编程 64.3
FrontierCode · 0.234232323232323 比例
Artificial Analysis · 独立评测 · 2.0
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; frontiercode-2-0
Vals Code Migration · 57.19%
Vals AI · 独立评测 · 1.1
Qwen3.8 Max (0902) / 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 62.1
GDP.pdf · 0.228 比例
Artificial Analysis · 独立评测 · current published task suite
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; gdp-pdf
SimpleQA Verified · 0.473 比例
Epoch AI · 独立评测 · run 1.2.0
qwen3.8-max-0902_xhigh · epoch-simpleqa-reviewed-method-20261029-task-version-1.2.0 · 2026-09-02公开
AA-Omniscience · 0.29533333333333334 比例
Artificial Analysis · 独立评测 · 1.1
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; omniscience-accuracy
AA-Omniscience · 0.7294228949858088 比例
Artificial Analysis · 独立评测 · 1.1
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; omniscience-non-hallucination
多模态理解 76.5
MMMU-Pro · 0.827745664739884 比例
Artificial Analysis · 独立评测 · Standard 10
Qwen3.8 Max (0902) · Artificial Analysis current published protocol; mmmu-pro