[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-image-service-v2-gemini-3-flash-preview":3,"text-service-v2-gemini-3-flash-preview":195},[4],{"id":5,"aliases":6,"types":7,"pricing_group":9,"pricing":10,"display_name":5,"capabilities":15,"model_capabilities":20,"model_capabilities_zh":93,"introduction":142,"introduction_zh":143,"description":144,"description_zh":145,"title_focus":146,"title_focus_zh":147,"keyword_extras":148,"keyword_extras_zh":151,"model_data":154},"gemini-3-flash-preview",[5],[8],"openai","google\u002Fgemini",{"flat_tokens":11},{"input_tokens":12,"output_tokens":13,"cache_read_tokens":14,"cache_write_tokens":12},"0.5","3","0.05",{"context_window":16,"max_output":17,"modalities":18},1048576,65536,[19],"text",{"groups":21,"highlights":82,"overall":86,"scenario":88,"summary":91,"weakness":92},[22,59,73],{"items":23,"name":58},[24,30,35,39,44,48,51,54],{"detail":25,"method":26,"name":27,"samples":28,"score":29},"","Mixed","Agent Collaboration",18,63,{"detail":25,"method":31,"name":32,"samples":33,"score":34},"Objective","Code Generation",12,73,{"detail":25,"method":26,"name":36,"samples":37,"score":38},"Code Comprehension & Debugging",6,67,{"detail":25,"method":40,"name":41,"samples":42,"score":43},"Subjective","Creative Writing",22,72,{"detail":25,"method":26,"name":45,"samples":46,"score":47},"Information Retrieval \u002F RAG",9,71,{"detail":25,"method":26,"name":49,"samples":50,"score":43},"Long-Context Handling",16,{"detail":25,"method":26,"name":52,"samples":53,"score":29},"Math & Science Reasoning",14,{"detail":25,"method":40,"name":55,"samples":56,"score":57},"Multilingual Capability",11,88,"Advanced Capabilities",{"items":60,"name":72},[61,65,69],{"detail":25,"method":26,"name":62,"samples":63,"score":64},"General Knowledge",10,91,{"detail":25,"method":40,"name":66,"samples":67,"score":68},"Text Comprehension",23,68,{"detail":25,"method":26,"name":70,"samples":50,"score":71},"Logical Reasoning",74,"General Foundations",{"items":74,"name":81},[75,78],{"detail":25,"method":40,"name":76,"samples":77,"score":34},"Hallucination Control",15,{"detail":25,"method":40,"name":79,"samples":28,"score":80},"Instruction Following",89,"Safety & Compliance",[83,84,85],{"name":62,"score":64},{"name":79,"score":80},{"name":55,"score":57},{"rating":87,"score":71},"良好",{"fit":89,"name":90},79,"Translation & Localization \u002F Customer Support \u002F Social Listening","Gemini 3 Flash scored 74 overall, performing well — an efficient model that keeps quality at speed. It stands out in general knowledge (91%), instruction following (89%) and multilingual capability (88%), staying reliable and format-compliant across languages, which fits high-volume translation and support work. Comparatively, agent collaboration (63%) is weak; multi-step tool chains need simplification. Fast, rule-following multilingual responses are its strength.",{"name":27,"note":25,"score":29},{"groups":94,"highlights":133,"overall":137,"scenario":138,"summary":140,"weakness":141},[95,117,126],{"items":96,"name":116},[97,100,103,105,108,110,112,114],{"detail":25,"method":98,"name":99,"samples":28,"score":29},"主\u002F客观混合","智能体协同",{"detail":25,"method":101,"name":102,"samples":33,"score":34},"客观","代码生成",{"detail":25,"method":98,"name":104,"samples":37,"score":38},"代码理解与调试",{"detail":25,"method":106,"name":107,"samples":42,"score":43},"主观","创意写作",{"detail":25,"method":98,"name":109,"samples":46,"score":47},"信息检索 \u002F RAG",{"detail":25,"method":98,"name":111,"samples":50,"score":43},"长文本处理",{"detail":25,"method":98,"name":113,"samples":53,"score":29},"数学与科学推理",{"detail":25,"method":106,"name":115,"samples":56,"score":57},"多语言能力","专项进阶能力",{"items":118,"name":125},[119,121,123],{"detail":25,"method":98,"name":120,"samples":63,"score":64},"通识知识",{"detail":25,"method":106,"name":122,"samples":67,"score":68},"文本理解",{"detail":25,"method":98,"name":124,"samples":50,"score":71},"逻辑推理","通用基础能力",{"items":127,"name":132},[128,130],{"detail":25,"method":106,"name":129,"samples":77,"score":34},"幻觉控制",{"detail":25,"method":106,"name":131,"samples":28,"score":80},"指令遵循","安全与合规能力",[134,135,136],{"name":120,"score":64},{"name":131,"score":80},{"name":115,"score":57},{"rating":87,"score":71},{"fit":89,"name":139},"翻译与本地化 \u002F 智能客服 \u002F 社媒舆情分析","Gemini 3 Flash 综合得分 74，整体表现良好，是一款速度与质量兼顾的高效模型。通识知识（91%）、指令遵循（89%）与多语言能力（88%）表现突出，跨语言场景下可靠且守规，适合高频翻译与客服任务。相对而言，智能体协同（63%）偏弱，多步骤工具链需简化。快速守规的多语言响应是它的强项。",{"name":99,"note":25,"score":29},"Gemini 3 Flash is Google's efficient model, strengthening general knowledge and instruction following while staying fast — suited to localization, customer support and social-listening at high volume.","Gemini 3 Flash是Google的高效模型，在保持快速响应的同时强化通识知识与指令遵循，适合翻译本地化、智能客服与社媒舆情分析等高频任务。","Gemini 3 Flash balances speed with knowledge Q&A and steady instruction following for high-frequency, multilingual content work. Integrate in one click via the SilvaMux unified API.","Gemini 3 Flash兼顾速度与知识问答能力，指令遵循稳定，适合高频调用与多语言内容处理。可通过 SilvaMux 统一 API 一键快速接入。","Efficient Fast Model","高效快速模型",[149,150],"fast response","multilingual",[152,153],"快速响应","多语言",{"summary":155,"recentAvailability":168,"observedAt":25,"bars":169,"metrics":173},[156,160,164],{"label":157,"value":158,"unit":159},"modelsDetail.performance.latency","12.44","s",{"label":161,"value":162,"unit":163},"modelsDetail.performance.throughput","99.71K","tokens\u002Fmin",{"label":165,"value":166,"unit":167},"modelsDetail.performance.availability","99.3","%","99.3%",{"degraded":170,"down":171},[],[172,46],30,[174,177,180,184,188,191],{"label":175,"value":176},"modelsDetail.performance.completionRate","95%",{"label":178,"value":179},"modelsDetail.performance.cacheHitRate","90%",{"label":181,"value":182,"unit":183},"modelsDetail.performance.tokenUsage","1,770,606,017","tokens",{"label":185,"value":186,"unit":187},"modelsDetail.performance.avgRequests","44","modelsDetail.performance.requestsUnit",{"label":189,"value":190,"unit":163},"modelsDetail.performance.tpm","99,711",{"label":192,"value":193,"unit":194},"modelsDetail.performance.qpm","867","req\u002Fmin",{"ttft":196,"tps":199,"e2e":201,"requests":204,"successfulRequests":205,"successRate":206,"availability":207},{"p50":197,"p95":198},376,1302,{"p50":64,"p95":200},92,{"p50":202,"p95":203},8966,9316,81686,79579,"97.42",[208,208,208,208,208,208,208,208,208,208,208,208,208,208,208,208,208,208,208,208,208,208,208,208],"up"]