Qwen3.7 Plus
开始使用
API 接入
Cloudflare AI Gateway API文档
目录部署标识：alibaba/qwen3.7-plus。具体区域、权限与价格以服务商为准。
Alibaba API文档
目录部署标识：qwen3.7-plus。具体区域、权限与价格以服务商为准。
Vercel AI Gateway API文档
目录部署标识：alibaba/qwen3.7-plus。具体区域、权限与价格以服务商为准。
LLM Gateway API文档
目录部署标识：alibaba/qwen3.7-plus。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 40.1 · 17项基准
推理求解 61.2
GPQA Diamond · 0.9 比例
Artificial Analysis · 独立评测 · Diamond
Qwen3.7 Plus · Current AA standalone protocol. Status verified in aa-method-current.md section gpqa-diamond
HLE · 0.139 比例
Artificial Analysis · 独立评测 · Diamond
Qwen3.7 Plus · Artificial Analysis current published protocol; hle-diamond
工具与任务执行 24.4
APEX-Agents · 0.224188790560472 比例
Artificial Analysis · 独立评测 · current published task suite
Qwen3.7 Plus · Artificial Analysis current published protocol; apex-agents-aa
tau3-Banking · 0.175257731958763 比例
Artificial Analysis · 独立评测 · 1.0.1
Qwen3.7 Plus · Current AA standalone protocol. Status verified in aa-method-current.md section tau3-banking
GDPval-AA · 774.8 分
Artificial Analysis · 独立评测 · 2.1
Qwen3.7 Plus · Artificial Analysis current published protocol; gdpval-aa-normalized
Terminal-Bench · 0.0101010101010101 比例
Artificial Analysis · 独立评测 · 4.0
Qwen3.7 Plus · Artificial Analysis current published protocol; terminalbench-4-0
AutomationBench · 0.17391220980015495 比例
Artificial Analysis · 独立评测 · current published task suite
Qwen3.7 Plus · Artificial Analysis current published protocol; automationbench-aa
AA-Briefcase · 915.35 分
Artificial Analysis · 独立评测 · 1.1
Qwen3.7 Plus · Artificial Analysis current published protocol; aa-briefcase
EnterpriseOps-Gym · 0.40555058191584603 比例
Artificial Analysis · 独立评测 · current published task suite
Qwen3.7 Plus · Artificial Analysis current published protocol; enterprise-ops-gym-aa
BFCL · 72.9
qwen.ai · 官方发布比较 · 4
Qwen3.7-Plus · Official published comparison; BFCL-V4; exact column Qwen3.7-Plus. Footnotes and all competing runs retained in source.
MCP Atlas · 73.2
qwen.ai · 官方发布比较 · 1000 tasks
Qwen3.7-Plus · Official published comparison; MCP-Atlas; exact column Qwen3.7-Plus. Footnotes and all competing runs retained in source.
编程 0.0
DeepSWE · 16.5
huggingface.co · 官方发布比较 · 1.1
Qwen3.7-Plus · Published page qwen38-flashnext; row Agentic coding DeepSWE 1.1; preserve page footnotes and task-specific settings · 2026-08-26公开
语言与信息处理 61.0
IFBench · 0.779591836734694 比例
Artificial Analysis · 独立评测 · current published task suite
Qwen3.7 Plus · Artificial Analysis current published protocol; ifbench
GDP.pdf · 0.122 比例
Artificial Analysis · 独立评测 · current published task suite
Qwen3.7 Plus · Artificial Analysis current published protocol; gdp-pdf
IFEval · 94.6
qwen.ai · 官方发布比较 · current maintainer dataset
Qwen3.7-Plus · Official published comparison; IFEval; exact column Qwen3.7-Plus. Footnotes and all competing runs retained in source.
MMLU-Pro · 88.5
qwen.ai · 官方发布比较 · current maintainer dataset
Qwen3.7-Plus · Official published comparison; MMLU-Pro; exact column Qwen3.7-Plus. Footnotes and all competing runs retained in source.
多模态理解 64.7
MMMU-Pro · 0.804624277456647 比例
Artificial Analysis · 独立评测 · Standard 10
Qwen3.7 Plus · Artificial Analysis current published protocol; mmmu-pro
资料来源
- 版本日期来源 · 版本资料 · 2026-10-29查阅
- qwen.ai · official_release_comparison · 2026-10-29查阅
- huggingface.co · official_release_comparison · 2026-10-29查阅