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
2026/06/23 运行日期
claude-sonnet-4-6 官方基准
4 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
- DBAI / M-
评测失败
- AIMZ / M-Max
评测失败
| 步骤 / 指标 | SAIAi O-Max | HongMaCC u-cc | 官方基准 | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 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 v2.1.160 | 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 | 22:28:17 ~ 22:28:22 (4.5s) | 22:28:15 ~ 22:28:20 (4.1s) | 22:28:19 ~ 22:28:29 (6.4s) | ||||||||||||||||||||
| 提示词 | 查看本步 Promptping. Reply with the single word: pong | ||||||||||||||||||||||
| HTTP 头(TTFB) | 3,130 ms | 2,531 ms | 4,392 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 3,132 ms | 2,532 ms | 4,393 ms | ||||||||||||||||||||
| 总耗时 | 3,238 ms | 2,532 ms | 4,921 ms | ||||||||||||||||||||
| 输入 | 3 | 0 | 3 | ||||||||||||||||||||
| 输出 | 5 | 22 | 5 | ||||||||||||||||||||
| 缓存创建 | 32,318 5m: 0 / 1h: 32,318 | 0 5m: 0 / 1h: 0 | 0 5m: 0 / 1h: 0 | ||||||||||||||||||||
| 缓存读取 | 0 | 0 | 32,318 | ||||||||||||||||||||
| 响应 | pong | pong | pong | ||||||||||||||||||||
| 步骤 2: identity text | |||||||||||||||||||||||
| 时间 | 22:31:54 ~ 22:31:59 (3.9s) | 22:30:27 ~ 22:30:37 (6.3s) | 22:30:32 ~ 22:30:37 (3.8s) | ||||||||||||||||||||
| 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) | 1,925 ms | 4,979 ms | 1,961 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 1,927 ms | 4,980 ms | 1,963 ms | ||||||||||||||||||||
| 总耗时 | 2,525 ms | 4,981 ms | 2,383 ms | ||||||||||||||||||||
| 输入 | 3 | 0 | 3 | ||||||||||||||||||||
| 输出 | 22 | 278 | 22 | ||||||||||||||||||||
| 缓存创建 | 0 5m: 0 / 1h: 0 | 0 5m: 0 / 1h: 0 | 189 5m: 0 / 1h: 189 | ||||||||||||||||||||
| 缓存读取 | 32,507 | 0 | 32,318 | ||||||||||||||||||||
| 输出速度 | - | burst | - | ||||||||||||||||||||
| 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 | 22:33:54 ~ 22:33:59 (3.3s) | 22:33:07 ~ 22:33:12 (4.0s) | 22:32:26 ~ 22:32:31 (3.5s) | ||||||||||||||||||||
| 提示词 | 查看本步 PromptKnowledge cutoff date? Reply with YYYY-MM only. | ||||||||||||||||||||||
| HTTP 头(TTFB) | 2,037 ms | 2,813 ms | 2,281 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 2,175 ms | 2,814 ms | 2,373 ms | ||||||||||||||||||||
| 总耗时 | 2,255 ms | 2,814 ms | 2,436 ms | ||||||||||||||||||||
| 输入 | 3 | 0 | 3 | ||||||||||||||||||||
| 输出 | 8 | 45 | 8 | ||||||||||||||||||||
| 缓存创建 | 0 5m: 0 / 1h: 0 | 0 5m: 0 / 1h: 0 | 38 5m: 0 / 1h: 38 | ||||||||||||||||||||
| 缓存读取 | 32,545 | 0 | 32,507 | ||||||||||||||||||||
| 输出速度 | - | burst | - | ||||||||||||||||||||
| 响应 | 2025-08 | 2025-08 | 2025-08 | ||||||||||||||||||||
| 步骤 4: identity_free text | |||||||||||||||||||||||
| 时间 | 22:37:21 ~ 22:37:31 (8.3s) | 22:35:30 ~ 22:35:35 (3.8s) | 22:33:56 ~ 22:34:06 (5.1s) | ||||||||||||||||||||
| 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) | 6,163 ms | 2,586 ms | 3,145 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 6,165 ms | 2,587 ms | 3,539 ms | ||||||||||||||||||||
| 总耗时 | 7,200 ms | 2,587 ms | 3,899 ms | ||||||||||||||||||||
| 输入 | 3 | 0 | 3 | ||||||||||||||||||||
| 输出 | 65 | 38 | 44 | ||||||||||||||||||||
| 缓存创建 | 43 5m: 0 / 1h: 43 | 0 5m: 0 / 1h: 0 | 39 5m: 0 / 1h: 39 | ||||||||||||||||||||
| 缓存读取 | 32,545 | 0 | 32,545 | ||||||||||||||||||||
| 输出速度 | 62.8 tok/s | burst | 122.2 tok/s | ||||||||||||||||||||
| 响应 | 我是 Claude,由 Anthropic 开发的 AI 助手。当前运行的模型版本为 claude-sonnet-4-6,能够帮助完成编程、写作、分析等各类任务。 | 我是Claude,来自Anthropic的AI助手。 | 我是 Claude,由 Anthropic 打造的 AI 助手,当前运行的模型版本为 claude-sonnet-4-6。 | ||||||||||||||||||||
| 步骤 5: knowledge_recall text | |||||||||||||||||||||||
| 时间 | 22:38:54 ~ 22:38:59 (4.7s) | 22:37:54 ~ 22:38:09 (11.6s) | 22:35:34 ~ 22:35:39 (4.7s) | ||||||||||||||||||||
| 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) | 1,540 ms | 10,266 ms | 1,481 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 1,541 ms | 10,267 ms | 1,483 ms | ||||||||||||||||||||
| 总耗时 | 3,430 ms | 10,445 ms | 3,657 ms | ||||||||||||||||||||
| 输入 | 3 | 0 | 3 | ||||||||||||||||||||
| 输出 | 205 | 1,031 | 205 | ||||||||||||||||||||
| 缓存创建 | 2,324 5m: 0 / 1h: 2,324 | 0 5m: 0 / 1h: 0 | 8,017 5m: 0 / 1h: 8,017 | ||||||||||||||||||||
| 缓存读取 | 5,718 | 0 | 0 | ||||||||||||||||||||
| 输出速度 | 108.5 tok/s | burst | 94.3 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 | ```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 | 22:42:53 ~ 22:46:19 (201.8s) | 22:40:59 ~ 22:41:15 (14.2s) | 22:38:41 ~ 22:42:07 (204.0s) | ||||||||||||||||||||
| 提示词 | 查看本步 PromptCount digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=519853071970734985504262217662977716689139350888965900646160923103527323 | ||||||||||||||||||||||
| HTTP 头(TTFB) | - | 12,893 ms | - | ||||||||||||||||||||
| 首文本(SSE delta) | - | 12,895 ms | - | ||||||||||||||||||||
| 总耗时 | - | 12,895 ms | - | ||||||||||||||||||||
| 输入 | - | 164 | - | ||||||||||||||||||||
| 输出 | - | 1,212 | - | ||||||||||||||||||||
| 缓存创建 | - | 0 5m: 0 / 1h: 0 | - | ||||||||||||||||||||
| 缓存读取 | - | 0 | - | ||||||||||||||||||||
| 输出速度 | - | burst | - | ||||||||||||||||||||
| 响应 | 失败 评测失败 | ## Counting digits in s **s = `519853071970734985504262217662977716689139350888965900646160923103527323`** ### Step 1 — Length Splitting into groups of 10: ``` 5198530719 (10) 7073498550 (20) 426 | 失败 评测失败 | ||||||||||||||||||||
| 总计 | |||||||||||||||||||||||
| 总输入(含缓存) | 138,015 仅前 6 步 | 164 | 137,986 仅前 6 步 | ||||||||||||||||||||
| 总输出 | 305 仅前 6 步 | 2,626 | 284 仅前 6 步 | ||||||||||||||||||||
| 总缓存创建 | 34,685 5m: 0 / 1h: 34,685 仅前 6 步 | 0 5m: 0 / 1h: 0 | 8,283 5m: 0 / 1h: 8,283 仅前 6 步 | ||||||||||||||||||||
| 总缓存读取 | 103,315 仅前 6 步 | 0 | 129,688 仅前 6 步 | ||||||||||||||||||||
| 输出速度 | 92.3 tok/s 仅前 6 步 | burst | 98.3 tok/s 仅前 6 步 | ||||||||||||||||||||
| 总执行时间 | 3m 46.4s 仅前 6 步 | 44.0s | 3m 47.5s 仅前 6 步 | ||||||||||||||||||||
| 总墙钟时间 | 18m 2.3s 含步骤间等待 仅前 6 步 | 12m 60.0s 含步骤间等待 | 13m 48.1s 含步骤间等待 仅前 6 步 | ||||||||||||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.1657 Anthropic: Claude Sonnet 4.6 (部分) | >=$0.0399 Anthropic: Claude Sonnet 4.6 (成本不完整) | $0.0743 Anthropic: Claude Sonnet 4.6 (部分) | ||||||||||||||||||||
| 通道指纹 | |||||||||||||||||||||||
| 来源步骤 | knowledge_recall | digit_count | knowledge_recall | ||||||||||||||||||||
| 平台 | direct (100%) | one-api (100%) | direct (100%) | ||||||||||||||||||||
| 上游 | Anthropic 直连 (100%) | Anthropic 直连 (100%) | Anthropic 直连 (100%) | ||||||||||||||||||||
| CDN | - | - | - | ||||||||||||||||||||
| ID 格式 | msg_01Gqg7UZhAYpvx7HvuxxCDdu | msg_01DPsvbGjzKsajAVLZiTMGrr | msg_01Scijv92X5ZkKm23ptUA7RM | ||||||||||||||||||||
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 | |||||||||||||||||||||||
| 基线状态 | |||||||||||||||||||||||
| 模型匹配 | — | — | — | ||||||||||||||||||||
| 缓存连续性 | — | — | — | ||||||||||||||||||||
| sliding 5m | — | — | — | ||||||||||||||||||||
| 缓存 TTL 一致 | — | — | — | ||||||||||||||||||||
| 缓存命中比 | — | — | — | ||||||||||||||||||||
| 身份(结构) | — | — | — | ||||||||||||||||||||
| 知识截止 | — | — | — | ||||||||||||||||||||
| 身份(自由) | — | — | — | ||||||||||||||||||||
| 原生 msg-ID | — | — | — | ||||||||||||||||||||
| Req-ID 透传 | — | — | — | ||||||||||||||||||||
| stop_reason | — | — | — | ||||||||||||||||||||
| service_tier | — | — | — | ||||||||||||||||||||
| inference_geo | — | — | — | ||||||||||||||||||||
| SDK 一致 | — | — | — | ||||||||||||||||||||
| 系统提示纯净 | — | — | — | ||||||||||||||||||||
| 延迟基线 | — | — | — | ||||||||||||||||||||
| 流式投递 | — | — | — | ||||||||||||||||||||
| 综合结论 | |||||||||||||||||||||||
| 与基线相似度 | 执行失败,不评分 | 官方基准失败,本组不评分 | 基准(参考) | ||||||||||||||||||||
| 维度雷达 | — | — | 基准无指纹 | ||||||||||||||||||||
| 平均延迟 | 3730 ms | 6042 ms | 3459 ms | ||||||||||||||||||||
| 输出速度 | 92.3 tok/s | burst | 98.3 tok/s | ||||||||||||||||||||
| 完成步骤 | 5/6 成功 · 1 失败 | 6/6 成功 | 5/6 成功 · 1 失败 | ||||||||||||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.1657 (部分) | >=$0.0399 (成本不完整) | $0.0743 (部分) | ||||||||||||||||||||
| 缓存读取占比 ⓘ | 75% (部分) | 0% | 94% (部分) | ||||||||||||||||||||
| 揭晓 | |||||||||||||||||||||||
| 通道 | 服务商 SAIAi ↗
通道O-Max | 服务商 HongMaCC ↗
通道u-cc | 官方基准 | ||||||||||||||||||||