[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-image-service-v2-gemini-3.6-flash":3,"text-service-v2-gemini-3.6-flash":198},[4],{"id":5,"aliases":6,"types":7,"pricing_group":9,"pricing":10,"display_name":5,"capabilities":15,"model_capabilities":20,"model_capabilities_zh":96,"introduction":145,"introduction_zh":146,"description":147,"description_zh":148,"title_focus":149,"title_focus_zh":150,"keyword_extras":151,"keyword_extras_zh":154,"model_data":157},"gemini-3.6-flash",[5],[8],"openai","google\u002Fgemini",{"flat_tokens":11},{"input_tokens":12,"output_tokens":13,"cache_read_tokens":14,"cache_write_tokens":12},"1.5","7.5","0.15",{"context_window":16,"max_output":17,"modalities":18},1048576,65536,[19],"text",{"groups":21,"highlights":84,"overall":88,"scenario":91,"summary":94,"weakness":95},[22,60,74],{"items":23,"name":59},[24,30,35,39,43,47,52,56],{"detail":25,"method":26,"name":27,"samples":28,"score":29},"","Mixed","Agent Collaboration",18,73,{"detail":25,"method":31,"name":32,"samples":33,"score":34},"Objective","Code Generation",12,58,{"detail":25,"method":26,"name":36,"samples":37,"score":38},"Code Comprehension & Debugging",6,71,{"detail":25,"method":26,"name":40,"samples":41,"score":42},"Creative Writing",22,69,{"detail":25,"method":26,"name":44,"samples":45,"score":46},"Information Retrieval \u002F RAG",9,70,{"detail":25,"method":48,"name":49,"samples":50,"score":51},"Subjective","Long-Context Handling",16,81,{"detail":25,"method":31,"name":53,"samples":54,"score":55},"Math & Science Reasoning",14,77,{"detail":25,"method":48,"name":57,"samples":58,"score":51},"Multilingual Capability",11,"Advanced Capabilities",{"items":61,"name":73},[62,66,70],{"detail":25,"method":26,"name":63,"samples":64,"score":65},"General Knowledge",10,89,{"detail":25,"method":48,"name":67,"samples":68,"score":69},"Text Comprehension",23,79,{"detail":25,"method":26,"name":71,"samples":50,"score":72},"Logical Reasoning",72,"General Foundations",{"items":75,"name":83},[76,80],{"detail":25,"method":26,"name":77,"samples":78,"score":79},"Hallucination Control",15,74,{"detail":25,"method":26,"name":81,"samples":28,"score":82},"Instruction Following",80,"Safety & Compliance",[85,86,87],{"name":63,"score":65},{"name":49,"score":51},{"name":57,"score":51},{"rating":89,"score":90},"良好",75,{"fit":92,"name":93},78,"Customer Support \u002F Translation & Localization \u002F Enterprise Knowledge Q&A","Gemini 3.6 Flash scored 75 overall, performing well — an efficient balanced model for daily volume. It stands out in general knowledge (89%), long-context handling (81%) and multilingual capability (81%), staying consistent over extended documents across languages, which fits customer support and knowledge-base Q&A. Comparatively, code generation (58%) is weak; coding work should go elsewhere. Fast, consistent knowledge responses at scale are its lane.",{"name":32,"note":25,"score":34},{"groups":97,"highlights":136,"overall":140,"scenario":141,"summary":143,"weakness":144},[98,120,129],{"items":99,"name":119},[100,103,106,108,110,112,115,117],{"detail":25,"method":101,"name":102,"samples":28,"score":29},"主\u002F客观混合","智能体协同",{"detail":25,"method":104,"name":105,"samples":33,"score":34},"客观","代码生成",{"detail":25,"method":101,"name":107,"samples":37,"score":38},"代码理解与调试",{"detail":25,"method":101,"name":109,"samples":41,"score":42},"创意写作",{"detail":25,"method":101,"name":111,"samples":45,"score":46},"信息检索 \u002F RAG",{"detail":25,"method":113,"name":114,"samples":50,"score":51},"主观","长文本处理",{"detail":25,"method":104,"name":116,"samples":54,"score":55},"数学与科学推理",{"detail":25,"method":113,"name":118,"samples":58,"score":51},"多语言能力","专项进阶能力",{"items":121,"name":128},[122,124,126],{"detail":25,"method":101,"name":123,"samples":64,"score":65},"通识知识",{"detail":25,"method":113,"name":125,"samples":68,"score":69},"文本理解",{"detail":25,"method":101,"name":127,"samples":50,"score":72},"逻辑推理","通用基础能力",{"items":130,"name":135},[131,133],{"detail":25,"method":101,"name":132,"samples":78,"score":79},"幻觉控制",{"detail":25,"method":101,"name":134,"samples":28,"score":82},"指令遵循","安全与合规能力",[137,138,139],{"name":123,"score":65},{"name":114,"score":51},{"name":118,"score":51},{"rating":89,"score":90},{"fit":92,"name":142},"智能客服 \u002F 翻译与本地化 \u002F 企业知识库问答","Gemini 3.6 Flash 综合得分 75，整体表现良好，是一款日常高频场景的高效均衡模型。通识知识（89%）、长文本处理（81%）与多语言能力（81%）表现突出，跨语言长文档中保持一致输出，在智能客服与知识库问答场景中表现稳定。相对而言，代码生成（58%）偏弱，编码工作建议交给其他模型。规模化快速知识响应是它的赛道。",{"name":105,"note":25,"score":34},"Gemini 3.6 Flash is Google's efficient multimodal model, balanced across knowledge and long-context work — suited to customer support, localization and enterprise knowledge bases.","Gemini 3.6 Flash是Google的高效多模态模型，在通识知识与长文本处理上表现均衡，适合智能客服、翻译本地化和企业知识库问答等日常高频场景。","Gemini 3.6 Flash balances speed with knowledge Q&A and steady long-context handling for high-volume business answers and content. Integrate in one click via the SilvaMux unified API.","Gemini 3.6 Flash兼顾速度与知识问答，长文本处理稳定，适合高频业务问答与内容处理。可通过 SilvaMux 统一 API 一键快速接入。","Efficient Balanced Model","高效均衡模型",[152,153],"fast response","knowledge Q&A",[155,156],"快速响应","知识问答",{"summary":158,"recentAvailability":171,"observedAt":25,"bars":172,"metrics":176},[159,163,167],{"label":160,"value":161,"unit":162},"modelsDetail.performance.latency","20.60","s",{"label":164,"value":165,"unit":166},"modelsDetail.performance.throughput","74.59K","tokens\u002Fmin",{"label":168,"value":169,"unit":170},"modelsDetail.performance.availability","98.8","%","98.8%",{"degraded":173,"down":175},[174],35,[],[177,180,183,187,191,194],{"label":178,"value":179},"modelsDetail.performance.completionRate","99%",{"label":181,"value":182},"modelsDetail.performance.cacheHitRate","84%",{"label":184,"value":185,"unit":186},"modelsDetail.performance.tokenUsage","2,795,211,656","tokens",{"label":188,"value":189,"unit":190},"modelsDetail.performance.avgRequests","40","modelsDetail.performance.requestsUnit",{"label":192,"value":193,"unit":166},"modelsDetail.performance.tpm","74,595",{"label":195,"value":196,"unit":197},"modelsDetail.performance.qpm","998","req\u002Fmin",{"ttft":199,"tps":202,"e2e":205,"requests":208,"successfulRequests":209,"successRate":210,"availability":211},{"p50":200,"p95":201},994,1911,{"p50":203,"p95":204},90,92,{"p50":206,"p95":207},7135,8026,111060,107831,"97.09",[212,212,212,212,212,212,212,212,212,212,212,212,212,212,212,212,213,212,212,212,212,212,212,212],"up","degraded"]