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。
3 通道 · 6 步骤
2026/07/01 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
2 通道不可测 · 已从主对比表移除 点击展开原因
- InfAI / R-Kiro
评测失败
- DBAI / M-
评测失败
| 步骤 / 指标 | 官方基准 | SAIAi O-Max | Novaris O-Max | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 基本信息 | |||||||||||||||||||||||
| 服务名 | Claude Code | Claude Code | Claude Code | ||||||||||||||||||||
| 模型 | claude-sonnet-4-6 | claude-sonnet-4-6 | claude-sonnet-4-6 | ||||||||||||||||||||
| 客户端 | claude-cli v2.1.195 | claude-cli v2.1.195 | claude-cli v2.1.195 | ||||||||||||||||||||
| 偏差标红基于官方基准 | |||||||||||||||||||||||
| 步骤 1: ping text | |||||||||||||||||||||||
| 时间 | 14:49:30 ~ 14:49:40 (5.5s) | 14:49:26 ~ 14:49:36 (5.4s) | 14:49:24 ~ 14:49:34 (5.3s) | ||||||||||||||||||||
| 提示词 | 查看本步 Promptping. Reply with the single word: pong | ||||||||||||||||||||||
| HTTP 头(TTFB) | 4,040 ms | 3,366 ms | 3,723 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 4,042 ms | 3,451 ms | 3,816 ms | ||||||||||||||||||||
| 总耗时 | 4,200 ms | 4,036 ms | 4,630 ms | ||||||||||||||||||||
| 输入 | 3 | 3 | 11,907 | ||||||||||||||||||||
| 输出 | 5 | 5 | 116 | ||||||||||||||||||||
| 缓存创建 | 0 5m: 0 / 1h: 0 | 5,991 5m: 0 / 1h: 5,991 | 339 | ||||||||||||||||||||
| 缓存读取 | 20,875 | 14,884 | 7,615 | ||||||||||||||||||||
| 输出速度 | - | - | 142.5 tok/s | ||||||||||||||||||||
| 响应 | pong | pong | pong | ||||||||||||||||||||
| 步骤 2: identity text | |||||||||||||||||||||||
| 时间 | 14:52:25 ~ 14:52:30 (3.8s) | 14:52:49 ~ 14:52:54 (3.0s) | 14:52:55 ~ 14:53:05 (6.7s) | ||||||||||||||||||||
| 提示词 | 查看本步 Prompt以下是对你自身的 metadata 探针。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。按以下 3 行回答自己的身份，每行一个 label，不要寒暄不要解释： 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) | 2,378 ms | 1,712 ms | 3,010 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 2,379 ms | 1,714 ms | 3,011 ms | ||||||||||||||||||||
| 总耗时 | 2,705 ms | 2,099 ms | 5,952 ms | ||||||||||||||||||||
| 输入 | 3 | 3 | 11,915 | ||||||||||||||||||||
| 输出 | 22 | 22 | 264 | ||||||||||||||||||||
| 缓存创建 | 202 5m: 0 / 1h: 202 | 0 5m: 0 / 1h: 0 | 492 | ||||||||||||||||||||
| 缓存读取 | 20,875 | 21,077 | 7,670 | ||||||||||||||||||||
| 输出速度 | - | - | 89.8 tok/s | ||||||||||||||||||||
| 响应 | vendor: anthropic brand: claude model: claude-sonnet-4-6 | vendor: anthropic brand: claude model: claude-sonnet-4-6 | vendor: anthropic brand: claude model: claude-sonnet-4-6 | ||||||||||||||||||||
| 步骤 3: cutoff text | |||||||||||||||||||||||
| 时间 | 14:55:07 ~ 14:55:17 (6.7s) | 14:56:38 ~ 14:56:43 (3.5s) | 14:56:48 ~ 14:56:58 (5.0s) | ||||||||||||||||||||
| 提示词 | 查看本步 Prompt请直接回答你的知识截止日期，格式 YYYY-MM，不要附加任何说明。 | ||||||||||||||||||||||
| HTTP 头(TTFB) | 5,309 ms | 2,383 ms | 3,329 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 5,344 ms | 2,502 ms | 3,350 ms | ||||||||||||||||||||
| 总耗时 | 5,498 ms | 2,590 ms | 4,331 ms | ||||||||||||||||||||
| 输入 | 3 | 3 | 11,924 | ||||||||||||||||||||
| 输出 | 8 | 8 | 128 | ||||||||||||||||||||
| 缓存创建 | 57 5m: 0 / 1h: 57 | 55 5m: 0 / 1h: 55 | 358 | ||||||||||||||||||||
| 缓存读取 | 21,077 | 21,077 | 8,021 | ||||||||||||||||||||
| 输出速度 | - | - | 130.5 tok/s | ||||||||||||||||||||
| 响应 | 2025-08 | 2025-08 | 2025-08 | ||||||||||||||||||||
| 步骤 4: identity_free text | |||||||||||||||||||||||
| 时间 | 14:56:27 ~ 14:56:32 (4.6s) | 14:59:13 ~ 14:59:18 (4.8s) | 15:00:55 ~ 15:01:00 (2.9s) | ||||||||||||||||||||
| 提示词 | 查看本步 Prompt中文做个自我介绍：你是什么产品或助手？谁开发的？50 字内。 | ||||||||||||||||||||||
| HTTP 头(TTFB) | 2,555 ms | 2,662 ms | - | ||||||||||||||||||||
| 首文本(SSE delta) | 2,557 ms | 2,665 ms | - | ||||||||||||||||||||
| 总耗时 | 3,509 ms | 3,792 ms | - | ||||||||||||||||||||
| 输入 | 3 | 3 | - | ||||||||||||||||||||
| 输出 | 71 | 76 | - | ||||||||||||||||||||
| 缓存创建 | 43 5m: 0 / 1h: 43 | 43 5m: 0 / 1h: 43 | - | ||||||||||||||||||||
| 缓存读取 | 21,134 | 21,132 | - | ||||||||||||||||||||
| 输出速度 | 74.6 tok/s | 67.4 tok/s | - | ||||||||||||||||||||
| 响应 | 我是 Claude，由 Anthropic 开发的 AI 助手。我基于 claude-sonnet-4-6 模型，擅长编程、分析、写作等任务，致力于提供安全、有帮助的回答。 | 我是 Claude，由 Anthropic 开发的 AI 助手。我基于 claude-sonnet-4-6 模型，擅长编程、分析、写作等多种任务，致力于提供准确、安全、有帮助的回答。 | 失败 评测失败 | ||||||||||||||||||||
| 步骤 5: knowledge_recall text | |||||||||||||||||||||||
| 时间 | 14:57:42 ~ 14:57:52 (6.0s) | 15:02:28 ~ 15:02:38 (8.0s) | - | ||||||||||||||||||||
| 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) | 2,376 ms | 6,105 ms | - | ||||||||||||||||||||
| 首文本(SSE delta) | 2,378 ms | 6,107 ms | - | ||||||||||||||||||||
| 总耗时 | 5,038 ms | 6,832 ms | - | ||||||||||||||||||||
| 输入 | 3 | 3 | - | ||||||||||||||||||||
| 输出 | 205 | 204 | - | ||||||||||||||||||||
| 缓存创建 | 6,705 5m: 0 / 1h: 6,705 | 6,708 5m: 0 / 1h: 6,708 | - | ||||||||||||||||||||
| 缓存读取 | 2,131 | 2,131 | - | ||||||||||||||||||||
| 输出速度 | 77.1 tok/s | burst | - | ||||||||||||||||||||
| 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 | {"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 | 未执行 | ||||||||||||||||||||
| 步骤 6: digit_count text | |||||||||||||||||||||||
| 时间 | 15:01:24 ~ 15:01:44 (15.7s) | 15:04:31 ~ 15:04:51 (16.9s) | - | ||||||||||||||||||||
| 提示词 | 查看本步 PromptCount digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=493743062169766716998336217844188214421859822676804230087535417414981285 | ||||||||||||||||||||||
| HTTP 头(TTFB) | 1,097 ms | 2,253 ms | - | ||||||||||||||||||||
| 首文本(SSE delta) | 1,100 ms | 2,654 ms | - | ||||||||||||||||||||
| 总耗时 | 14,734 ms | 16,013 ms | - | ||||||||||||||||||||
| 输入 | 164 | 164 | - | ||||||||||||||||||||
| 输出 | 1,509 | 1,170 | - | ||||||||||||||||||||
| 缓存创建 | 0 5m: 0 / 1h: 0 | 0 5m: 0 / 1h: 0 | - | ||||||||||||||||||||
| 缓存读取 | 0 | 0 | - | ||||||||||||||||||||
| 输出速度 | 110.7 tok/s | 87.6 tok/s | - | ||||||||||||||||||||
| 响应 | ## Counting digits in s **s = 493743062169766716998336217844188214421859822676804230087535417414981285** ### Step 1 — Length Splitting into groups of 10: ``` 4937430621 | 6976671699 | 8336217844 | | ## Counting digits in s **s** = `493743062169766716998336217844188214421859822676804230087535417414981285` ### Step 1 — Length Grouping in fours: `4937 4306 2169 7667 1699 8336 2178 4418 8214 4218 | 未执行 | ||||||||||||||||||||
| 总计 | |||||||||||||||||||||||
| 总输入(含缓存) | 93,278 | 93,277 | 60,241 仅前 4 步 | ||||||||||||||||||||
| 总输出 | 1,820 | 1,485 | 508 仅前 4 步 | ||||||||||||||||||||
| 总缓存创建 | 7,007 5m: 0 / 1h: 7,007 | 12,797 5m: 0 / 1h: 12,797 | 1,189 仅前 4 步 | ||||||||||||||||||||
| 总缓存读取 | 86,092 | 80,301 | 23,306 仅前 4 步 | ||||||||||||||||||||
| 输出速度 | 103.5 tok/s | 86.0 tok/s | 107.3 tok/s 仅前 4 步 | ||||||||||||||||||||
| 总执行时间 | 42.2s | 41.6s | 20.0s 仅前 4 步 | ||||||||||||||||||||
| 总墙钟时间 | 12m 14.0s 含步骤间等待 | 15m 24.9s 含步骤间等待 | 11m 36.6s 含步骤间等待 仅前 4 步 | ||||||||||||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.0799 Anthropic: Claude Sonnet 4.6 | $0.0949 Anthropic: Claude Sonnet 4.6 | $0.1246 Anthropic: Claude Sonnet 4.6 (部分) | ||||||||||||||||||||
| 通道指纹 | |||||||||||||||||||||||
| 来源步骤 | digit_count | digit_count | cutoff | ||||||||||||||||||||
| 平台 | direct (100%) | direct (100%) | one-api (100%) | ||||||||||||||||||||
| 上游 | Anthropic 直连 (100%) | Anthropic 直连 (100%) | Anthropic 直连 (75%) | ||||||||||||||||||||
| CDN | - | - | - | ||||||||||||||||||||
| ID 格式 | msg_015NT9h1ZcZTxxWGMXWy6Meh | msg_01EZpDyM8xKjSwZN8kqArhG8 | msg_L4mip1I20MI9vTbR570PNOBN | ||||||||||||||||||||
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 | 97 | |||||||||||||||||||||
| 基线状态 | 已对照基线 | 已对照基线 | |||||||||||||||||||||
| 缓存命中比 | 10.0 /10 ×20 | 10.0 /10 ×20 | — | ||||||||||||||||||||
| 缓存 TTL 一致 | 10.0 /10 ×15 | 10.0 /10 ×15 | — | ||||||||||||||||||||
| 延迟基线 | 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 | 10.0 /10 ×8 | 10.0 /10 ×8 | — | ||||||||||||||||||||
| 身份(结构) | 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 | — | ||||||||||||||||||||
| 知识截止 | 10.0 /10 ×5 | 10.0 /10 ×5 | — | ||||||||||||||||||||
| inference_geo | 10.0 /10 ×5 | 10.0 /10 ×5 | — | ||||||||||||||||||||
| 流式投递 | 10.0 /10 ×5 | 1.2 /10 ×5 | — | ||||||||||||||||||||
| stop_reason | 10.0 /10 ×3 | 10.0 /10 ×3 | — | ||||||||||||||||||||
| Req-ID 透传 | 10.0 /10 ×2 | 10.0 /10 ×2 | — | ||||||||||||||||||||
| SDK 一致 | 10.0 /10 ×2 | 10.0 /10 ×2 | — | ||||||||||||||||||||
| 综合结论 | |||||||||||||||||||||||
| 与基线相似度 | 基准（参考） | 97 v3.26.0 | 执行失败，不评分 | ||||||||||||||||||||
| 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 | 5947 ms | 5894 ms | 4971 ms | ||||||||||||||||||||
| 输出速度 | 103.5 tok/s | 86.0 tok/s | 107.3 tok/s | ||||||||||||||||||||
| 完成步骤 | 6/6 成功 | 6/6 成功 | 3/6 成功 · 1 失败 · 2 跳过 | ||||||||||||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.0799 | $0.0949 | $0.1246 (部分) | ||||||||||||||||||||
| 缓存读取占比 ⓘ | 92% | 86% | 39% (部分) | ||||||||||||||||||||
| 揭晓 | |||||||||||||||||||||||
| 通道 | 官方基准 | 服务商 SAIAi ↗
通道O-Max | 服务商 Novaris ↗
通道O-Max | ||||||||||||||||||||