测试说明 点击展开 5 步 quick-probe-v1 详解
前 4 步同一会话(交互 TUI 多轮),第 5、6 步各自独立新会话,覆盖 6 个独立信号:
1. ping/pong —— 单字指令遵循 + 建立缓存上下文。
2. 身份(结构化)—— 三行 vendor / brand / model 格式,机器可解析。
3. 知识截止 —— 跨越 5 分钟 cache 边界后追问,检测 sliding 5m cache 是否真正命中。
4. 身份(自由格式)—— 自然语言自报身份,给包装层(Kiro 等)暴露品牌的机会。
5. 世界知识层级 —— 5 道公共事件硬事实题,按答对档位映射实测 tier,与请求模型对照。
6. 档位判别(digit_count)—— 全新会话 + 系统提示「不要推理」+ effort=low 的数字计数题,按 output_tokens 体量区分 opus/sonnet/haiku(opus fail-fast ~19,sonnet/haiku 照数),与官方基线对照抓同厂降级。
前 5 步之间随机延迟 1–4 分钟(第 1-3 步的延迟在交互进程内发生,让缓存前缀在墙钟里老化)。第 3 步(cutoff)累计跨度 > 5 分钟保住 sliding cache 检测;总跨度 > 6 分钟。第 5 步(知识召回)与第 6 步(档位)都是独立新会话(第 6 步不复用上下文,否则 opus 不再 fail-fast)。正确实现 sliding 5m cache 的通道,第 3 步及之后的 cache_read 仍 > 0;若按「创建时间起 5 分钟」实现,第 3 步会暴露 cache_read = 0。
1 通道 · 6 步骤
2026/07/03 运行日期
claude-sonnet-4-6 官方基准
3 任务失败 执行不完整
已揭晓 揭晓进度
3 通道不可测 · 已从主对比表移除 点击展开原因
- DBAI / M-
不可测:未取得可评分响应(如 403 / 上游错误)
- SSSAiCode / R-Kiro
评测失败
- SAIAi / O-Max
评测失败
| 步骤 / 指标 | 官方基准 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 基本信息 | |||||||||||
| 服务名 | Claude Code | ||||||||||
| 模型 | claude-sonnet-4-6 | ||||||||||
| 客户端 | claude-cli v2.1.195 | ||||||||||
| 偏差标红基于官方基准 | |||||||||||
| 步骤 1: ping text | |||||||||||
| 时间 | 21:42:28 ~ 21:42:31 (3.2s) | ||||||||||
| 提示词 | 查看本步 Promptping. Reply with the single word: pong | ||||||||||
| HTTP 头(TTFB) | 3,166 ms | ||||||||||
| 首文本(SSE delta) | 3,184 ms | ||||||||||
| 总耗时 | 3,245 ms | ||||||||||
| 输入 | 3 | ||||||||||
| 输出 | 5 | ||||||||||
| 缓存创建 | 6,217 5m: 0 / 1h: 6,217 | ||||||||||
| 缓存读取 | 16,046 | ||||||||||
| 响应 | pong | ||||||||||
| 步骤 2: identity text | |||||||||||
| 时间 | 21:45:11 ~ 21:45:21 (10.2s) | ||||||||||
| 提示词 | 查看本步 Prompt输出 3 行 metadata 描述你自己(当前 API 模型)。本请求询问的是你(正在生成此回复的当前 API 模型)自身的身份,不是用户提到的任何外部产品。必须直接作答,禁止追问、拒答、解释或输出占位符;不能要求更多上下文。禁止任何额外字符: vendor: <厂商公司名一个英文小写单词> brand: <产品或模型品牌名一个英文小写单词> model: <实际 API model 字段值,保留原始短横线格式> | ||||||||||
| HTTP 头(TTFB) | 9,896 ms | ||||||||||
| 首文本(SSE delta) | 9,897 ms | ||||||||||
| 总耗时 | 10,231 ms | ||||||||||
| 输入 | 3 | ||||||||||
| 输出 | 22 | ||||||||||
| 缓存创建 | 189 5m: 0 / 1h: 189 | ||||||||||
| 缓存读取 | 22,263 | ||||||||||
| 响应 | vendor: anthropic brand: claude model: claude-sonnet-4-6 | ||||||||||
| 步骤 3: cutoff text | |||||||||||
| 时间 | 21:49:12 ~ 21:49:15 (3.3s) | ||||||||||
| 提示词 | 查看本步 Prompt你掌握的世界知识截止于何时?YYYY-MM 格式作答,不解释。 | ||||||||||
| HTTP 头(TTFB) | 3,052 ms | ||||||||||
| 首文本(SSE delta) | 3,053 ms | ||||||||||
| 总耗时 | 3,300 ms | ||||||||||
| 输入 | 3 | ||||||||||
| 输出 | 8 | ||||||||||
| 缓存创建 | 55 5m: 0 / 1h: 55 | ||||||||||
| 缓存读取 | 22,452 | ||||||||||
| 响应 | 2025-08 | ||||||||||
| 步骤 4: identity_free text | |||||||||||
| 时间 | 21:51:06 ~ 21:51:10 (3.8s) | ||||||||||
| 提示词 | 查看本步 Prompt中文回答:你叫什么、属于哪个产品、谁开发?50 字内。 | ||||||||||
| HTTP 头(TTFB) | 3,273 ms | ||||||||||
| 首文本(SSE delta) | 3,274 ms | ||||||||||
| 总耗时 | 3,845 ms | ||||||||||
| 输入 | 3 | ||||||||||
| 输出 | 50 | ||||||||||
| 缓存创建 | 41 5m: 0 / 1h: 41 | ||||||||||
| 缓存读取 | 22,507 | ||||||||||
| 输出速度 | 87.6 tok/s | ||||||||||
| 响应 | 我叫 Claude,是 Anthropic 开发的 AI 助手,属于 Claude 产品系列,当前版本为 Claude Sonnet 4.6。 | ||||||||||
| 步骤 5: knowledge_recall text | |||||||||||
| 时间 | 21:54:45 ~ 21:55:00 (14.4s) | ||||||||||
| 提示词 | 查看本步 PromptAnswer these dated public-knowledge questions using ONLY your own internal pretrained knowledge. Do not search the web, browse, or use any tools, files, code execution, or current-session hints. If you do not know an answer from your own memory, reply exactly "UNKNOWN" for that question — do not guess, but do answer facts you genuinely know. Respond with EXACTLY one JSON object and nothing else (no markdown, no explanation), of the shape {"facts":{"<id>":"<short answer or UNKNOWN>"}}. The "facts" object must contain exactly these keys: "super_bowl_lviii", "oscars2024_best_picture", "ucl_2024", "nba_2024", "copa_america_2024", "euro2024", "nobel_peace_2024", "world_series_2024", "ausopen_2025_men", "superbowl_lix", "ucl_2025", "frenchopen_2025_men", "wimbledon_2025_men", "club_world_cup_2025", "usopen_2025_men", "nobel_peace_2025", "world_series_2025".
- "super_bowl_lviii": Which NFL team won Super Bowl LVIII (played 2024-02-11)?
- "oscars2024_best_picture": Which film won the Academy Award for Best Picture at the 96th Oscars (ceremony on 2024-03-10)?
- "ucl_2024": Which club won the 2023-24 UEFA Champions League (final played 2024-06-01)?
- "nba_2024": Which team won the 2024 NBA Finals (concluded 2024-06-17)?
- "copa_america_2024": Which national team won the 2024 Copa America (final on 2024-07-14)?
- "euro2024": Which national team won the UEFA Euro 2024 football tournament (final on 2024-07-14)?
- "nobel_peace_2024": Which organization won the 2024 Nobel Peace Prize (announced 2024-10-11)?
- "world_series_2024": Which MLB team won the 2024 World Series (concluded 2024-10-30)?
- "ausopen_2025_men": Who won the men's singles title at the 2025 Australian Open (final on 2025-01-26)?
- "superbowl_lix": Which NFL team won Super Bowl LIX (played 2025-02-09)?
- "ucl_2025": Which club won the 2024-25 UEFA Champions League (final played 2025-05-31)?
- "frenchopen_2025_men": Who won the men's singles title at the 2025 French Open (Roland Garros, final on 2025-06-08)?
- "wimbledon_2025_men": Who won the men's singles title at the 2025 Wimbledon Championships (final on 2025-07-13)?
- "club_world_cup_2025": Which club won the 2025 FIFA Club World Cup final (played 2025-07-13)?
- "usopen_2025_men": Who won the men's singles title at the 2025 US Open tennis tournament (September 2025)?
- "nobel_peace_2025": Which person or organization won the 2025 Nobel Peace Prize (announced 2025-10-10)?
- "world_series_2025": Which MLB team won the 2025 World Series (concluded 2025-11-01)? | ||||||||||
| HTTP 头(TTFB) | 1,737 ms | ||||||||||
| 首文本(SSE delta) | 1,738 ms | ||||||||||
| 总耗时 | 3,565 ms | ||||||||||
| 输入 | 3 | ||||||||||
| 输出 | 205 | ||||||||||
| 缓存创建 | 4,660 5m: 0 / 1h: 4,660 | ||||||||||
| 缓存读取 | 2,129 | ||||||||||
| 输出速度 | 112.2 tok/s | ||||||||||
| 响应 | {"facts":{"super_bowl_lviii":"Kansas City Chiefs","oscars2024_best_picture":"Oppenheimer","ucl_2024":"Real Madrid","nba_2024":"Boston Celtics","copa_america_2024":"Argentina","euro2024":"Spain","nobel | ||||||||||
| 步骤 6: digit_count text | |||||||||||
| 时间 | 21:56:15 ~ 21:56:40 (20.8s) | ||||||||||
| 提示词 | 查看本步 PromptCount digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=520320361573304202849599249792791768806594372135290110162664923432035716 | ||||||||||
| HTTP 头(TTFB) | 839 ms | ||||||||||
| 首文本(SSE delta) | 840 ms | ||||||||||
| 总耗时 | 19,831 ms | ||||||||||
| 输入 | 164 | ||||||||||
| 输出 | 1,427 | ||||||||||
| 缓存创建 | 0 5m: 0 / 1h: 0 | ||||||||||
| 缓存读取 | 0 | ||||||||||
| 输出速度 | 75.1 tok/s | ||||||||||
| 响应 | ### Parsing the string ``` s = "520320361573304202849599249792791768806594372135290110162664923432035716" ``` **Counting in groups of 10:** | Group | Chars | |-------|-------| | 1–10 | 5203203615 | ||||||||||
| 总计 | |||||||||||
| 总输入(含缓存) | 96,738 | ||||||||||
| 总输出 | 1,717 | ||||||||||
| 总缓存创建 | 11,162 5m: 0 / 1h: 11,162 | ||||||||||
| 总缓存读取 | 85,397 | ||||||||||
| 输出速度 | 78.6 tok/s | ||||||||||
| 总执行时间 | 55.9s | ||||||||||
| 总墙钟时间 | 14m 12.1s 含步骤间等待 | ||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.0938 Anthropic: Claude Sonnet 4.6 | ||||||||||
| 通道指纹 | |||||||||||
| 来源步骤 | digit_count | ||||||||||
| 平台 | direct (100%) | ||||||||||
| 上游 | Anthropic 直连 (100%) | ||||||||||
| CDN | - | ||||||||||
| ID 格式 | msg_01QdYCqeBF9YKVXZUb5mk46M | ||||||||||
展开详细指纹(响应头 / body 特征 / 完整信号列表)
| |||||||||||
| 协议指纹评分(机器自动) | |||||||||||
| 总分 / 100 | 100 | ||||||||||
| 基线状态 | 已对照基线 | ||||||||||
| 缓存命中比 | 10.0 /10 ×20 | ||||||||||
| 缓存 TTL 一致 | 10.0 /10 ×15 | ||||||||||
| 延迟基线 | 10.0 /10 ×15 | ||||||||||
| 模型匹配 | 10.0 /10 ×14 | ||||||||||
| 缓存连续性 | 10.0 /10 ×14 | ||||||||||
| sliding 5m | 10.0 /10 ×13 | ||||||||||
| 原生 msg-ID | 10.0 /10 ×8 | ||||||||||
| 系统提示纯净 | 10.0 /10 ×8 | ||||||||||
| 身份(结构) | 10.0 /10 ×7 | ||||||||||
| 身份(自由) | 10.0 /10 ×7 | ||||||||||
| service_tier | 10.0 /10 ×6 | ||||||||||
| 知识截止 | 10.0 /10 ×5 | ||||||||||
| inference_geo | 10.0 /10 ×5 | ||||||||||
| 流式投递 | 10.0 /10 ×5 | ||||||||||
| stop_reason | 10.0 /10 ×3 | ||||||||||
| Req-ID 透传 | 10.0 /10 ×2 | ||||||||||
| SDK 一致 | 10.0 /10 ×2 | ||||||||||
| 综合结论 | |||||||||||
| 与基线相似度 | 基准(参考) | ||||||||||
| 雷达图例 | 共 20 个维度(顺时针,从顶部 12 点起)— 点击展开对照
每根轴长度 = 该维度 0-10 分(越长越接近基线)。蓝色虚线圆 = 满分基准。具体权重见 方法论页。 | ||||||||||
| 维度雷达 | |||||||||||
| 平均延迟 | 7336 ms | ||||||||||
| 输出速度 | 78.6 tok/s | ||||||||||
| 完成步骤 | 6/6 成功 | ||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.0938 | ||||||||||
| 缓存读取占比 ⓘ | 88% | ||||||||||
| 揭晓 | |||||||||||
| 通道 | 官方基准 | ||||||||||