Grok 4.7
开始使用
API 接入
CommandCode API文档
目录部署标识：xai/grok-4.7。具体区域、权限与价格以服务商为准。
Merge Gateway API文档
目录部署标识：xai/grok-4.7。具体区域、权限与价格以服务商为准。
Tempr Gateway API文档
目录部署标识：xai/grok-4.7。具体区域、权限与价格以服务商为准。
Cloudflare AI Gateway API文档
目录部署标识：xai/grok-4.7。具体区域、权限与价格以服务商为准。
Vertex API文档
目录部署标识：xai/grok-4.7。具体区域、权限与价格以服务商为准。
Eden AI API文档
目录部署标识：xai/grok-4.7。具体区域、权限与价格以服务商为准。
xAI API文档
目录部署标识：grok-4.7。具体区域、权限与价格以服务商为准。
Perplexity Agent API文档
目录部署标识：xai/grok-4.7。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 69.2 · 14项基准
推理求解 63.3
Terminal-Bench-Science · 10.00%
Vals AI · 独立评测 · 0.1.0
Grok 4.7 / Mini-SWE-agent · Current displayed evaluator row. Mini-SWE-agent. Scores are not pooled across harnesses; source methodology and repeat counts retained.
HLE · 0.232 比例
Artificial Analysis · 独立评测 · Diamond
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; hle-diamond
CritPt · 0.335 比例
Artificial Analysis · 独立评测 · 2 Hard
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; critpt-v2-hard
工具与任务执行 83.8
GDPval-AA · 1718.42 分
Artificial Analysis · 独立评测 · 2.1
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; gdpval-aa-normalized
Terminal-Bench · 0.257575757575758 比例
Artificial Analysis · 独立评测 · 4.0
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; terminalbench-4-0
AutomationBench · 0.6555835148969458 比例
Artificial Analysis · 独立评测 · current published task suite
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; automationbench-aa
AA-Briefcase · 1637.4 分
Artificial Analysis · 独立评测 · 1.1
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; aa-briefcase
AA-AnalystAgent · 0.525 比例
Artificial Analysis · 独立评测 · current AA pass^5
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; aa-analyst-agent
编程 68.6
FrontierCode · 0.286575505050505 比例
Artificial Analysis · 独立评测 · 2.0
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; frontiercode-2-0
Vals Code Migration · 53.22%
Vals AI · 独立评测 · 1.1
Grok 4.7 / 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 73.0
GDP.pdf · 0.2 比例
Artificial Analysis · 独立评测 · current published task suite
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; gdp-pdf
SimpleQA Verified · 0.56 比例
Epoch AI · 独立评测 · run 1.2.0
grok-4.7_xhigh · epoch-simpleqa-reviewed-method-20261029-task-version-1.2.0 · 2026-09-22公开
AA-Omniscience · 0.427 比例
Artificial Analysis · 独立评测 · 1.1
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; omniscience-accuracy
AA-Omniscience · 0.7998836532867947 比例
Artificial Analysis · 独立评测 · 1.1
Grok 4.7 (Xhigh) · Artificial Analysis current published protocol; omniscience-non-hallucination
多模态理解 41.2
MMMU-Pro · 0.78150289017341 比例
Artificial Analysis · 独立评测 · Standard 10
Grok 4.7 (Low) · Artificial Analysis current published protocol; mmmu-pro