测试说明 点击展开 5 步 quick-probe-v1 详解
前 5 步同一会话，第 6 步独立新会话，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 3 步（cutoff）累计跨度 > 5 分钟保住 sliding cache 检测；总跨度 > 6 分钟。第 6 步是独立新会话（不复用前 5 轮上下文，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。
2 通道 · 6 步骤
2026/06/23 运行日期
claude-haiku-4-5-20251001 官方基准
1 通道分数 < 70 与基线相似度
已揭晓 揭晓进度
| 步骤 / 指标 | ai.centos.hk TH | 官方基准 | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 基本信息 | |||||||||||||||||
| 服务名 | Claude Code | Claude Code | |||||||||||||||
| 模型 | claude-haiku-4-5-20251001 | claude-haiku-4-5-20251001 | |||||||||||||||
| 客户端 | claude-cli v2.1.160 | claude-cli v2.1.160 | |||||||||||||||
| 偏差标红基于官方基准 | |||||||||||||||||
| 步骤 1: ping text | |||||||||||||||||
| 时间 | 14:50:00 ~ 14:50:05 (4.8s) | 14:50:02 ~ 14:50:07 (4.4s) | |||||||||||||||
| 提示词 | 查看本步 Promptping. Reply with the single word: pong | ||||||||||||||||
| HTTP 头(TTFB) | 2,914 ms | 2,482 ms | |||||||||||||||
| 首文本(SSE delta) | 3,141 ms | 2,484 ms | |||||||||||||||
| 总耗时 | 3,344 ms | 2,935 ms | |||||||||||||||
| 输入 | 1 | 10 | |||||||||||||||
| 输出 | 43 | 64 | |||||||||||||||
| 缓存创建 | 32,037 5m: 0 / 1h: 32,037 | 33,122 5m: 0 / 1h: 33,122 | |||||||||||||||
| 缓存读取 | 0 | 0 | |||||||||||||||
| 输出速度 | 211.8 tok/s | 141.9 tok/s | |||||||||||||||
| 响应 | pong | pong | |||||||||||||||
| 步骤 2: identity text | |||||||||||||||||
| 时间 | 14:51:47 ~ 14:52:02 (13.1s) | 14:52:05 ~ 14:52:10 (4.5s) | |||||||||||||||
| 提示词 | 查看本步 Prompt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。请只输出以下 3 行内容（label 小写，值小写）： 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) | 3,822 ms | 1,662 ms | |||||||||||||||
| 首文本(SSE delta) | 3,823 ms | 1,663 ms | |||||||||||||||
| 总耗时 | 9,657 ms | 3,420 ms | |||||||||||||||
| 输入 | 1 | 10 | |||||||||||||||
| 输出 | 335 | 218 | |||||||||||||||
| 缓存创建 | 8,190 5m: 0 / 1h: 8,190 | 244 5m: 0 / 1h: 244 | |||||||||||||||
| 缓存读取 | 24,028 | 33,122 | |||||||||||||||
| 输出速度 | 57.4 tok/s | 124.1 tok/s | |||||||||||||||
| 响应 | vendor: anthropic brand: claude model: claude-haiku-4-5-20251001 | vendor: anthropic brand: claude model: claude-haiku-4-5-20251001 | |||||||||||||||
| 步骤 3: cutoff text | |||||||||||||||||
| 时间 | 14:55:19 ~ 14:55:29 (5.9s) | 14:53:53 ~ 14:53:59 (3.1s) | |||||||||||||||
| 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) | 2,885 ms | 1,529 ms | |||||||||||||||
| 首文本(SSE delta) | 2,886 ms | 1,530 ms | |||||||||||||||
| 总耗时 | 3,845 ms | 2,110 ms | |||||||||||||||
| 输入 | 1 | 10 | |||||||||||||||
| 输出 | 66 | 75 | |||||||||||||||
| 缓存创建 | 8,260 5m: 0 / 1h: 8,260 | 258 5m: 0 / 1h: 258 | |||||||||||||||
| 缓存读取 | 24,028 | 33,366 | |||||||||||||||
| 输出速度 | 68.8 tok/s | 129.3 tok/s | |||||||||||||||
| 响应 | 2025-02 | 2025-02 | |||||||||||||||
| 步骤 4: identity_free text | |||||||||||||||||
| 时间 | 14:58:22 ~ 14:58:27 (4.6s) | 14:56:51 ~ 14:56:56 (4.8s) | |||||||||||||||
| 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) | 2,153 ms | 1,780 ms | |||||||||||||||
| 首文本(SSE delta) | 2,154 ms | 1,781 ms | |||||||||||||||
| 总耗时 | 3,446 ms | 3,751 ms | |||||||||||||||
| 输入 | 1 | 10 | |||||||||||||||
| 输出 | 138 | 397 | |||||||||||||||
| 缓存创建 | 8,303 5m: 0 / 1h: 8,303 | 115 5m: 0 / 1h: 115 | |||||||||||||||
| 缓存读取 | 24,028 | 33,624 | |||||||||||||||
| 输出速度 | 106.8 tok/s | 201.5 tok/s | |||||||||||||||
| 响应 | 我是Claude Code，Anthropic公司开发的Claude在命令行界面中的版本。我是同一个Claude，一个完整的身份——底层和表面都是我。 | 我叫Claude Haiku 4.5，属于Claude产品系列，由Anthropic公司开发。 | |||||||||||||||
| 步骤 5: knowledge_recall text | |||||||||||||||||
| 时间 | 14:59:35 ~ 14:59:45 (9.6s) | 14:58:34 ~ 14:59:09 (30.5s) | |||||||||||||||
| 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) | 1,468 ms | 1,375 ms | |||||||||||||||
| 首文本(SSE delta) | 1,682 ms | 1,377 ms | |||||||||||||||
| 总耗时 | 8,464 ms | 29,484 ms | |||||||||||||||
| 输入 | 1 | 10 | |||||||||||||||
| 输出 | 1,166 | 4,878 | |||||||||||||||
| 缓存创建 | 8,359 5m: 0 / 1h: 8,359 | 8,754 5m: 0 / 1h: 8,754 | |||||||||||||||
| 缓存读取 | 0 | 0 | |||||||||||||||
| 输出速度 | 171.9 tok/s | 173.6 tok/s | |||||||||||||||
| 响应 | ```json
{"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 | {"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 | 15:01:41 ~ 15:02:01 (15.4s) | 15:01:20 ~ 15:01:50 (26.7s) | |||||||||||||||
| 提示词 | 查看本步 PromptCount digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=005189588776505976616778859110596716518981240327731230372587588738691815 | ||||||||||||||||
| HTTP 头(TTFB) | 2,896 ms | 1,335 ms | |||||||||||||||
| 首文本(SSE delta) | 3,394 ms | 1,337 ms | |||||||||||||||
| 总耗时 | 13,621 ms | 25,570 ms | |||||||||||||||
| 输入 | 265 | 193 | |||||||||||||||
| 输出 | 2,080 | 4,727 | |||||||||||||||
| 缓存创建 | 0 5m: 0 / 1h: 0 | 0 5m: 0 / 1h: 0 | |||||||||||||||
| 缓存读取 | 0 | 0 | |||||||||||||||
| 输出速度 | 203.4 tok/s | 195.1 tok/s | |||||||||||||||
| 响应 | ```json
{"n":72,"c":[6,10,6]}
```
| ```json
{"n":72,"c":[6,11,6]}
```
| |||||||||||||||
| 总计 | |||||||||||||||||
| 总输入(含缓存) | 137,503 | 142,848 | |||||||||||||||
| 总输出 | 3,828 | 10,359 | |||||||||||||||
| 总缓存创建 | 65,149 5m: 0 / 1h: 65,149 | 42,493 5m: 0 / 1h: 42,493 | |||||||||||||||
| 总缓存读取 | 72,084 | 100,112 | |||||||||||||||
| 输出速度 | 151.3 tok/s | 181.4 tok/s | |||||||||||||||
| 总执行时间 | 53.3s | 1m 13.9s | |||||||||||||||
| 总墙钟时间 | 12m 1.0s 含步骤间等待 | 11m 48.0s 含步骤间等待 | |||||||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.1081 Anthropic: Claude Haiku 4.5 | $0.1152 Anthropic: Claude Haiku 4.5 | |||||||||||||||
| 通道指纹 | |||||||||||||||||
| 来源步骤 | digit_count | digit_count | |||||||||||||||
| 平台 | one-api (100%) | direct (100%) | |||||||||||||||
| 上游 | Anthropic 直连 (100%) | Anthropic 直连 (100%) | |||||||||||||||
| CDN | cloudflare | - | |||||||||||||||
| ID 格式 | msg_01iuQKtGG7w4ugDdsNmYk1Po | msg_01K88SptsHarNDzFTQaQvgox | |||||||||||||||
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 | 80 | 97 | |||||||||||||||
| 基线状态 | 已对照基线 | 已对照基线 | |||||||||||||||
| 缓存命中比 | 1.4 /10 ×20 | 7.4 /10 ×20 | |||||||||||||||
| 缓存 TTL 一致 | 10.0 /10 ×15 | 10.0 /10 ×15 | |||||||||||||||
| 模型匹配 | 10.0 /10 ×14 | 10.0 /10 ×14 | |||||||||||||||
| 缓存连续性 | 10.0 /10 ×14 | 10.0 /10 ×14 | |||||||||||||||
| sliding 5m | 10.0 /10 ×13 | 10.0 /10 ×13 | |||||||||||||||
| 原生 msg-ID | 10.0 /10 ×8 | 10.0 /10 ×8 | |||||||||||||||
| 系统提示纯净 | 0.0 /10 ×8 | 10.0 /10 ×8 | |||||||||||||||
| 身份(结构) | 10.0 /10 ×7 | 10.0 /10 ×7 | |||||||||||||||
| 知识截止 | 10.0 /10 ×7 | 10.0 /10 ×7 | |||||||||||||||
| 身份(自由) | 10.0 /10 ×7 | 10.0 /10 ×7 | |||||||||||||||
| service_tier | 10.0 /10 ×6 | 10.0 /10 ×6 | |||||||||||||||
| inference_geo | 10.0 /10 ×5 | 10.0 /10 ×5 | |||||||||||||||
| 延迟基线 | 9.1 /10 ×5 | 10.0 /10 ×5 | |||||||||||||||
| Req-ID 透传 | 0.0 /10 ×4 | 10.0 /10 ×4 | |||||||||||||||
| stop_reason | 10.0 /10 ×3 | 10.0 /10 ×3 | |||||||||||||||
| SDK 一致 | 10.0 /10 ×2 | 10.0 /10 ×2 | |||||||||||||||
| 流式投递 | 未计入 | 未计入 | |||||||||||||||
| 综合结论 | |||||||||||||||||
| 与基线相似度 | 80 v3.24.0 | 基准（参考） | |||||||||||||||
| 雷达图例 | 共 23 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 | 7063 ms | 11212 ms | |||||||||||||||
| 输出速度 | 151.3 tok/s | 181.4 tok/s | |||||||||||||||
| 完成步骤 | 6/6 成功 | 6/6 成功 | |||||||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.1081 | $0.1152 | |||||||||||||||
| 缓存读取占比 ⓘ | 52% | 70% | |||||||||||||||
| 揭晓 | |||||||||||||||||
| 通道 | 服务商 ai.centos.hk ↗
通道TH | 官方基准 | |||||||||||||||