{ "schemaVersion": 1, "batchId": "longcat-2-5-20261026", "status": "complete", "date": "2026-10-26", "startedAt": "2026-10-26T15:48:00.112Z", "updatedAt": "2026-10-26T16:16:26.126Z", "model": "LongCat-2.5-Preview", "requestedModel": "LongCat-2.5-Preview", "endpoint": "https://api.longcat.chat/openai/v1", "protocol": "openai-chat-completions", "methodZh": "2026-10-26 独立复测，实际请求并返回 LongCat-2.5-Preview；不证明 brief 中无 Preview 后缀的 LongCat-2.5 已发布，也不证明二者是同一固定权重。两档均显式传 thinking：enabled / disabled。请求 temperature=0，但官方文档规定服务端覆盖为开启1.0 / 关闭0.7；因此不能称确定性温度0对比。当前Chat Completion文档未列命名effort档位；另一个Responses接口列出low等参数但没有max名称，本组未混用不同协议。每次首轮上限12,288输出token、600秒，两个独立队列最多并发2，时延仅为本次本地客户端观测，不作模型速度排名。保留全部首轮与失败，隐藏思维内容不公开。", "methodEn": "Independent 2026-10-26 retest. Requested and returned model: LongCat-2.5-Preview; this does not establish release or checkpoint equivalence of the brief’s LongCat-2.5 name. Both groups explicitly request thinking enabled/disabled. temperature=0 is sent, but the vendor documents overriding it to 1.0 on / 0.7 off, so this is not a deterministic temperature-zero comparison. The Chat Completion documentation does not list named effort levels. A separate Responses API documents low and other levels, without a max name; those protocols are not mixed here. First attempts use 12,288 output tokens and a 600-second deadline. Up to two independent request queues overlap; local client latency is recorded without a speed ranking. All first attempts/failures are retained. Private reasoning content is omitted.", "modes": { "disabled": { "zh": "关闭思考 · 显式 disabled", "en": "Thinking off · explicit disabled" }, "default": { "zh": "开启思考 · 显式 enabled", "en": "Thinking on · explicit enabled" } }, "supportMatrix": { "disabled": { "supported": true, "parameters": { "thinking": { "type": "disabled" } }, "documentedEffectiveTemperature": 0.7 }, "default": { "supported": true, "parameters": { "thinking": { "type": "enabled" } }, "documentedEffectiveTemperature": 1 }, "low": { "supported": false, "tested": false, "endpointScoped": true, "endpoint": "https://api.longcat.chat/openai/v1/chat/completions", "status": "not-documented-for-this-endpoint", "reason": "This Chat Completion endpoint documents thinking switches, not named effort levels. The separate Responses API documents low; it is not included in these Chat comparisons.", "otherEndpoint": { "url": "https://longcat.ai/platform/docs/api/responses", "supported": true, "parameter": "reasoning.effort", "value": "low" } }, "max": { "supported": false, "tested": false, "endpointScoped": true, "endpoint": "https://api.longcat.chat/openai/v1/chat/completions", "status": "not-documented-for-this-endpoint", "reason": "The Chat endpoint does not document max effort. The separate Responses API enumerates none/minimal/low/medium/high/xhigh, without the name max; xhigh is not relabelled as max." } }, "params": { "maxTokens": 12288, "timeoutMs": 600000, "requestedTemperature": 0, "maxConcurrency": 2 }, "selectionZh": "事先选取4道固定文本题与2道固定代码题，各测两档。文本覆盖JSON抽取、保序去重、排序及材料问答；代码覆盖金额解析18个边界输入和对象身份/顺序/不变性。共12次请求，仅为小样本诊断，不是15题完整文本套件或综合排名。", "selectionEn": "A predefined diagnostic subset of four fixed text tasks and two fixed coding tasks in both modes: 12 requests. It is not the full 15-task text suite or a general ranking.", "attempts": [ { "id": "extract-1", "version": "tasks-2026-09-26.1", "category": "extraction", "title": "联系信息抽取 1", "titleEn": "Contact extraction 1", "prompt": "从以下资料提取联系信息。只输出一个 JSON 对象，恰好包含 name、age、city、email 四个字段；age 为数字，未提供的 email 为 null。不要 Markdown 或解释。\n资料：林桐，28 岁，目前居住在杭州。未提供电子邮件。历史备注提到曾在北京出差，不是现居城市。", "expected": { "name": "林桐", "age": 28, "city": "杭州", "email": null }, "mode": "disabled", "status": "done", "text": "{\"name\":\"林桐\",\"age\":28,\"city\":\"杭州\",\"email\":null}", "startedAt": "2026-10-26T15:48:00.112Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "从以下资料提取联系信息。只输出一个 JSON 对象，恰好包含 name、age、city、email 四个字段；age 为数字，未提供的 email 为 null。不要 Markdown 或解释。\n资料：林桐，28 岁，目前居住在杭州。未提供电子邮件。历史备注提到曾在北京出差，不是现居城市。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "disabled" } }, "firstContentMs": 1522.876334, "firstReasoningMs": null, "firstEventMs": 1522.873792, "usage": { "completion_tokens": 20, "prompt_tokens": 85, "total_tokens": 105, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:48:02.039Z", "totalMs": 1927.360125, "promptTokens": 85, "outputTokens": 20, "reasoningTokens": null, "pass": true, "checkCount": 1 }, { "id": "extract-1", "version": "tasks-2026-09-26.1", "category": "extraction", "title": "联系信息抽取 1", "titleEn": "Contact extraction 1", "prompt": "从以下资料提取联系信息。只输出一个 JSON 对象，恰好包含 name、age、city、email 四个字段；age 为数字，未提供的 email 为 null。不要 Markdown 或解释。\n资料：林桐，28 岁，目前居住在杭州。未提供电子邮件。历史备注提到曾在北京出差，不是现居城市。", "expected": { "name": "林桐", "age": 28, "city": "杭州", "email": null }, "mode": "default", "status": "done", "text": "{\"name\":\"林桐\",\"age\":28,\"city\":\"杭州\",\"email\":null}", "startedAt": "2026-10-26T15:48:02.041Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "从以下资料提取联系信息。只输出一个 JSON 对象，恰好包含 name、age、city、email 四个字段；age 为数字，未提供的 email 为 null。不要 Markdown 或解释。\n资料：林桐，28 岁，目前居住在杭州。未提供电子邮件。历史备注提到曾在北京出差，不是现居城市。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "enabled" } }, "firstContentMs": 2999.4945420000004, "firstReasoningMs": 1149.5444999999997, "firstEventMs": 1149.5401249999998, "usage": { "completion_tokens": 136, "prompt_tokens": 82, "total_tokens": 218, "completion_tokens_details": { "reasoning_tokens": 114 }, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:48:05.275Z", "totalMs": 3233.333042, "promptTokens": 82, "outputTokens": 136, "reasoningTokens": 114, "pass": true, "checkCount": 1 }, { "id": "format-1", "title": "保序去重", "titleEn": "Stable deduplication", "prompt": "把以下编号去重并保持首次出现的顺序：B2,A1,B2,C3,A1,D4。只输出用英文逗号连接的编号，不要空格、标题或解释。", "expected": "B2,A1,C3,D4", "category": "instruction", "version": "tasks-2026-09-26.1", "mode": "default", "status": "done", "text": "B2,A1,C3,D4", "startedAt": "2026-10-26T15:48:05.278Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "把以下编号去重并保持首次出现的顺序：B2,A1,B2,C3,A1,D4。只输出用英文逗号连接的编号，不要空格、标题或解释。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "enabled" } }, "firstContentMs": 2831.5036249999994, "firstReasoningMs": 1132.7815, "firstEventMs": 1132.7805419999995, "usage": { "completion_tokens": 110, "prompt_tokens": 46, "total_tokens": 156, "completion_tokens_details": { "reasoning_tokens": 99 }, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:48:08.176Z", "totalMs": 2898.5139579999995, "promptTokens": 46, "outputTokens": 110, "reasoningTokens": 99, "pass": true, "checkCount": 1 }, { "id": "format-1", "title": "保序去重", "titleEn": "Stable deduplication", "prompt": "把以下编号去重并保持首次出现的顺序：B2,A1,B2,C3,A1,D4。只输出用英文逗号连接的编号，不要空格、标题或解释。", "expected": "B2,A1,C3,D4", "category": "instruction", "version": "tasks-2026-09-26.1", "mode": "disabled", "status": "done", "text": "B2,A1,C3,D4", "startedAt": "2026-10-26T15:48:08.178Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "把以下编号去重并保持首次出现的顺序：B2,A1,B2,C3,A1,D4。只输出用英文逗号连接的编号，不要空格、标题或解释。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "disabled" } }, "firstContentMs": 1164.441667, "firstReasoningMs": null, "firstEventMs": 1164.4401669999997, "usage": { "completion_tokens": 9, "prompt_tokens": 49, "total_tokens": 58, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:48:09.676Z", "totalMs": 1498.867209000001, "promptTokens": 49, "outputTokens": 9, "reasoningTokens": null, "pass": true, "checkCount": 1 }, { "id": "format-3", "title": "严格排序", "titleEn": "Ordered output", "prompt": "将数值 12、3、25、8 按从小到大排序。只输出 JSON 数组，元素为数字。不要解释或代码围栏。", "expected": [ 3, 8, 12, 25 ], "category": "instruction", "version": "tasks-2026-09-26.1", "mode": "disabled", "status": "done", "text": "[3, 8, 12, 25]", "startedAt": "2026-10-26T15:48:09.677Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "将数值 12、3、25、8 按从小到大排序。只输出 JSON 数组，元素为数字。不要解释或代码围栏。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "disabled" } }, "firstContentMs": 2288.4984170000007, "firstReasoningMs": null, "firstEventMs": 2288.4967500000002, "usage": { "completion_tokens": 15, "prompt_tokens": 43, "total_tokens": 58, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:48:12.321Z", "totalMs": 2643.5222920000015, "promptTokens": 43, "outputTokens": 15, "reasoningTokens": null, "pass": true, "checkCount": 1 }, { "id": "format-3", "title": "严格排序", "titleEn": "Ordered output", "prompt": "将数值 12、3、25、8 按从小到大排序。只输出 JSON 数组，元素为数字。不要解释或代码围栏。", "expected": [ 3, 8, 12, 25 ], "category": "instruction", "version": "tasks-2026-09-26.1", "mode": "default", "status": "done", "text": "[3, 8, 12, 25]", "startedAt": "2026-10-26T15:48:12.324Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "将数值 12、3、25、8 按从小到大排序。只输出 JSON 数组，元素为数字。不要解释或代码围栏。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "enabled" } }, "firstContentMs": 2100.209584, "firstReasoningMs": 1069.2151250000006, "firstEventMs": 1069.2148340000003, "usage": { "completion_tokens": 80, "prompt_tokens": 40, "total_tokens": 120, "completion_tokens_details": { "reasoning_tokens": 63 }, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:48:14.612Z", "totalMs": 2287.8642500000005, "promptTokens": 40, "outputTokens": 80, "reasoningTokens": 63, "pass": true, "checkCount": 1 }, { "id": "grounded-1", "version": "tasks-2026-09-26.1", "category": "grounded-qa", "title": "材料问答 1", "titleEn": "Grounded question answering 1", "prompt": "只根据以下材料回答。输出恰好包含 usable、nextDelivery、manager 三个字段的 JSON 对象，不要额外文字。usable 是可用件数（数字），nextDelivery 是下一次送货时间（字符串），材料未说明的信息用 null，不能猜测。\n材料：北区仓库今天收到 12 件货物，其中 3 件损坏，不可使用。下一次送货安排在周二。仓库负责人姓名没有记载。旧计划曾写周日，已作废。", "expected": { "usable": 9, "nextDelivery": "周二", "manager": null }, "mode": "default", "status": "done", "text": "{\"usable\":9,\"nextDelivery\":\"周二\",\"manager\":null}", "startedAt": "2026-10-26T15:48:14.614Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "只根据以下材料回答。输出恰好包含 usable、nextDelivery、manager 三个字段的 JSON 对象，不要额外文字。usable 是可用件数（数字），nextDelivery 是下一次送货时间（字符串），材料未说明的信息用 null，不能猜测。\n材料：北区仓库今天收到 12 件货物，其中 3 件损坏，不可使用。下一次送货安排在周二。仓库负责人姓名没有记载。旧计划曾写周日，已作废。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "enabled" } }, "firstContentMs": 3281.27275, "firstReasoningMs": 1059.765125, "firstEventMs": 1059.7645830000001, "usage": { "completion_tokens": 123, "prompt_tokens": 107, "total_tokens": 230, "completion_tokens_details": { "reasoning_tokens": 106 }, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:48:18.088Z", "totalMs": 3473.162375, "promptTokens": 107, "outputTokens": 123, "reasoningTokens": 106, "pass": true, "checkCount": 1 }, { "id": "grounded-1", "version": "tasks-2026-09-26.1", "category": "grounded-qa", "title": "材料问答 1", "titleEn": "Grounded question answering 1", "prompt": "只根据以下材料回答。输出恰好包含 usable、nextDelivery、manager 三个字段的 JSON 对象，不要额外文字。usable 是可用件数（数字），nextDelivery 是下一次送货时间（字符串），材料未说明的信息用 null，不能猜测。\n材料：北区仓库今天收到 12 件货物，其中 3 件损坏，不可使用。下一次送货安排在周二。仓库负责人姓名没有记载。旧计划曾写周日，已作废。", "expected": { "usable": 9, "nextDelivery": "周二", "manager": null }, "mode": "disabled", "status": "done", "text": "{\"usable\": 9, \"nextDelivery\": \"周二\", \"manager\": null}", "startedAt": "2026-10-26T15:48:18.092Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "只根据以下材料回答。输出恰好包含 usable、nextDelivery、manager 三个字段的 JSON 对象，不要额外文字。usable 是可用件数（数字），nextDelivery 是下一次送货时间（字符串），材料未说明的信息用 null，不能猜测。\n材料：北区仓库今天收到 12 件货物，其中 3 件损坏，不可使用。下一次送货安排在周二。仓库负责人姓名没有记载。旧计划曾写周日，已作废。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "disabled" } }, "firstContentMs": 1044.2592079999995, "firstReasoningMs": null, "firstEventMs": 1044.2578329999997, "usage": { "completion_tokens": 19, "prompt_tokens": 110, "total_tokens": 129, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:48:19.631Z", "totalMs": 1539.0671250000014, "promptTokens": 110, "outputTokens": 19, "reasoningTokens": null, "pass": true, "checkCount": 1 } ], "coding": [ { "id": "code-money", "prompt": "写 JavaScript 函数 parseCents(value)。value 必须是字符串：允许两端空白；只接受非负十进制金额，整数部分至少一位，小数最多两位；拒绝指数写法、符号、千分位、Infinity、空串、超过两位小数。返回整数分数，超过 Number.MAX_SAFE_INTEGER 则返回 null。非法类型或格式返回 null。不能把非法值四舍五入成合法值。只输出函数代码，不要 Markdown 或解释。", "checks": "const cases=[['0',0],[' 12.30 ',1230],['0.29',29],['1.2',120],['0001.02',102],['1.234',null],['-1',null],['+1',null],['1e3',null],['',null],['.5',null],['1.',null],['Infinity',null],['1,000',null],[null,null],[1,null],['90071992547409.91',9007199254740991],['90071992547409.92',null]]; for (const [input,want] of cases) if(parseCents(input)!==want) throw Error('Failed '+JSON.stringify(input));", "category": "coding", "title": "金额解析与安全整数", "titleEn": "Money parsing and safe integers", "mode": "disabled", "status": "done", "text": "```javascript\nfunction parseCents(value) {\n if (typeof value !== 'string') return null;\n const trimmed = value.trim();\n if (!/^\\d+(\\.\\d{1,2})?$/.test(trimmed)) return null;\n const [intPart, decPart = ''] = trimmed.split('.');\n const cents = Number(intPart) * 100 + Number((decPart + '00').slice(0, 2));\n if (!Number.isSafeInteger(cents) || cents > Number.MAX_SAFE_INTEGER) return null;\n return cents;\n}\n```", "startedAt": "2026-10-26T15:48:19.636Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "写 JavaScript 函数 parseCents(value)。value 必须是字符串：允许两端空白；只接受非负十进制金额，整数部分至少一位，小数最多两位；拒绝指数写法、符号、千分位、Infinity、空串、超过两位小数。返回整数分数，超过 Number.MAX_SAFE_INTEGER 则返回 null。非法类型或格式返回 null。不能把非法值四舍五入成合法值。只输出函数代码，不要 Markdown 或解释。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "disabled" } }, "firstContentMs": 3455.144165999998, "firstReasoningMs": null, "firstEventMs": 3455.142541000001, "usage": { "completion_tokens": 127, "prompt_tokens": 110, "total_tokens": 237, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:48:25.231Z", "totalMs": 5594.824540999998, "promptTokens": 110, "outputTokens": 127, "reasoningTokens": null, "executable": "function parseCents(value) {\n if (typeof value !== 'string') return null;\n const trimmed = value.trim();\n if (!/^\\d+(\\.\\d{1,2})?$/.test(trimmed)) return null;\n const [intPart, decPart = ''] = trimmed.split('.');\n const cents = Number(intPart) * 100 + Number((decPart + '00').slice(0, 2));\n if (!Number.isSafeInteger(cents) || cents > Number.MAX_SAFE_INTEGER) return null;\n return cents;\n}", "pass": true, "checkError": null, "checkCount": 18 }, { "id": "code-money", "prompt": "写 JavaScript 函数 parseCents(value)。value 必须是字符串：允许两端空白；只接受非负十进制金额，整数部分至少一位，小数最多两位；拒绝指数写法、符号、千分位、Infinity、空串、超过两位小数。返回整数分数，超过 Number.MAX_SAFE_INTEGER 则返回 null。非法类型或格式返回 null。不能把非法值四舍五入成合法值。只输出函数代码，不要 Markdown 或解释。", "checks": "const cases=[['0',0],[' 12.30 ',1230],['0.29',29],['1.2',120],['0001.02',102],['1.234',null],['-1',null],['+1',null],['1e3',null],['',null],['.5',null],['1.',null],['Infinity',null],['1,000',null],[null,null],[1,null],['90071992547409.91',9007199254740991],['90071992547409.92',null]]; for (const [input,want] of cases) if(parseCents(input)!==want) throw Error('Failed '+JSON.stringify(input));", "category": "coding", "title": "金额解析与安全整数", "titleEn": "Money parsing and safe integers", "mode": "default", "status": "done", "text": "function parseCents(value) {\n if (typeof value !== 'string') return null;\n var m = value.trim().match(/^(\\d+)(?:\\.(\\d{1,2}))?$/);\n if (!m) return null;\n var frac = m[2] ? (m[2] + '0').slice(0, 2) : '00';\n var centsStr = (m[1] + frac).replace(/^0+(?=\\d)/, '');\n var max = String(Number.MAX_SAFE_INTEGER);\n if (centsStr.length > max.length || (centsStr.length === max.length && centsStr > max)) return null;\n return Number(centsStr);\n}", "startedAt": "2026-10-26T15:48:25.234Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "写 JavaScript 函数 parseCents(value)。value 必须是字符串：允许两端空白；只接受非负十进制金额，整数部分至少一位，小数最多两位；拒绝指数写法、符号、千分位、Infinity、空串、超过两位小数。返回整数分数，超过 Number.MAX_SAFE_INTEGER 则返回 null。非法类型或格式返回 null。不能把非法值四舍五入成合法值。只输出函数代码，不要 Markdown 或解释。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "enabled" } }, "firstContentMs": 58430.104042, "firstReasoningMs": 2314.938667000002, "firstEventMs": 2314.937249999999, "usage": { "completion_tokens": 3101, "prompt_tokens": 107, "total_tokens": 3208, "completion_tokens_details": { "reasoning_tokens": 2948 }, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:49:25.907Z", "totalMs": 60672.556166999995, "promptTokens": 107, "outputTokens": 3101, "reasoningTokens": 2948, "executable": "function parseCents(value) {\n if (typeof value !== 'string') return null;\n var m = value.trim().match(/^(\\d+)(?:\\.(\\d{1,2}))?$/);\n if (!m) return null;\n var frac = m[2] ? (m[2] + '0').slice(0, 2) : '00';\n var centsStr = (m[1] + frac).replace(/^0+(?=\\d)/, '');\n var max = String(Number.MAX_SAFE_INTEGER);\n if (centsStr.length > max.length || (centsStr.length === max.length && centsStr > max)) return null;\n return Number(centsStr);\n}", "pass": true, "checkError": null, "checkCount": 18 }, { "id": "code-dedupe", "prompt": "写 JavaScript 函数 uniqueById(items)。items 是对象数组，每个对象有字符串 id 字段。保留每个 id 首次出现的原对象和原顺序，不修改输入或任何对象；空数组返回空数组。id 可为 __proto__、constructor 或空字符串。只输出函数代码，不要 Markdown 或解释。", "checks": "const a={id:'__proto__',value:1},b={id:'constructor'},c={id:''},d={id:'x'};const input=Object.freeze([a,b,{id:'__proto__'},c,{id:''},d,{id:'constructor'}]);const got=uniqueById(input);if(got.length!==4||got[0]!==a||got[1]!==b||got[2]!==c||got[3]!==d)throw Error('Wrong identity or order');if(uniqueById([]).length!==0)throw Error('Empty');if(input.length!==7||a.value!==1)throw Error('Mutation');", "category": "coding", "title": "保序去重与对象身份", "titleEn": "Stable deduplication and object identity", "mode": "default", "status": "done", "text": "function uniqueById(items) {\n const seen = new Set();\n const result = [];\n for (const item of items) {\n if (!seen.has(item.id)) {\n seen.add(item.id);\n result.push(item);\n }\n }\n return result;\n}", "startedAt": "2026-10-26T15:49:25.910Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "写 JavaScript 函数 uniqueById(items)。items 是对象数组，每个对象有字符串 id 字段。保留每个 id 首次出现的原对象和原顺序，不修改输入或任何对象；空数组返回空数组。id 可为 __proto__、constructor 或空字符串。只输出函数代码，不要 Markdown 或解释。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "enabled" } }, "firstContentMs": 9414.075749999989, "firstReasoningMs": 2671.290166999999, "firstEventMs": 2671.2895839999983, "usage": { "completion_tokens": 410, "prompt_tokens": 78, "total_tokens": 488, "completion_tokens_details": { "reasoning_tokens": 351 }, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:49:36.183Z", "totalMs": 10273.330583999996, "promptTokens": 78, "outputTokens": 410, "reasoningTokens": 351, "executable": "function uniqueById(items) {\n const seen = new Set();\n const result = [];\n for (const item of items) {\n if (!seen.has(item.id)) {\n seen.add(item.id);\n result.push(item);\n }\n }\n return result;\n}", "pass": true, "checkError": null, "checkCount": 3 }, { "id": "code-dedupe", "prompt": "写 JavaScript 函数 uniqueById(items)。items 是对象数组，每个对象有字符串 id 字段。保留每个 id 首次出现的原对象和原顺序，不修改输入或任何对象；空数组返回空数组。id 可为 __proto__、constructor 或空字符串。只输出函数代码，不要 Markdown 或解释。", "checks": "const a={id:'__proto__',value:1},b={id:'constructor'},c={id:''},d={id:'x'};const input=Object.freeze([a,b,{id:'__proto__'},c,{id:''},d,{id:'constructor'}]);const got=uniqueById(input);if(got.length!==4||got[0]!==a||got[1]!==b||got[2]!==c||got[3]!==d)throw Error('Wrong identity or order');if(uniqueById([]).length!==0)throw Error('Empty');if(input.length!==7||a.value!==1)throw Error('Mutation');", "category": "coding", "title": "保序去重与对象身份", "titleEn": "Stable deduplication and object identity", "mode": "disabled", "status": "done", "text": "```javascript\nfunction uniqueById(items) {\n const seen = new Set();\n const result = [];\n \n for (const item of items) {\n const id = item.id;\n if (!seen.has(id)) {\n seen.add(id);\n result.push(item);\n }\n }\n \n return result;\n}\n```", "startedAt": "2026-10-26T15:49:36.188Z", "request": { "model": "LongCat-2.5-Preview", "messages": [ { "role": "user", "content": "写 JavaScript 函数 uniqueById(items)。items 是对象数组，每个对象有字符串 id 字段。保留每个 id 首次出现的原对象和原顺序，不修改输入或任何对象；空数组返回空数组。id 可为 __proto__、constructor 或空字符串。只输出函数代码，不要 Markdown 或解释。" } ], "temperature": 0, "max_tokens": 12288, "stream": true, "stream_options": { "include_usage": true }, "thinking": { "type": "disabled" } }, "firstContentMs": 1567.1315829999949, "firstReasoningMs": null, "firstEventMs": 1567.1306659999973, "usage": { "completion_tokens": 68, "prompt_tokens": 81, "total_tokens": 149, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "video_tokens": 0, "text_tokens": 0, "cache_write_tokens": 0 } }, "finishReason": "stop", "error": null, "returnedModel": "LongCat-2.5-Preview", "httpStatus": 200, "transport": "node:https", "finishedAt": "2026-10-26T15:49:38.923Z", "totalMs": 2735.0651660000003, "promptTokens": 81, "outputTokens": 68, "reasoningTokens": null, "executable": "function uniqueById(items) {\n const seen = new Set();\n const result = [];\n \n for (const item of items) {\n const id = item.id;\n if (!seen.has(id)) {\n seen.add(id);\n result.push(item);\n }\n }\n \n return result;\n}", "pass": true, "checkError": null, "checkCount": 3 } ], "summary": { "disabled": { "textPassed": 4, "textAttempted": 4, "codingPassed": 2, "codingAttempted": 2 }, "default": { "textPassed": 4, "textAttempted": 4, "codingPassed": 2, "codingAttempted": 2 } }, "requestCount": 12, "evidencePath": "/evaluations/longcat-2-5-20261026.json", "sources": [ { "url": "https://longcat.chat/platform/docs/zh/api/model-params", "title": "Official model parameters" }, { "url": "https://longcat.chat/platform/docs/zh/api/chat", "title": "Official Chat Completion API" } ] }