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-haiku-4-5-20251001 官方基准
1 通道分数 < 70 另含 2 任务失败
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
- Aiberm / cc
评测失败
- SudoCode / M-Max
评测失败
| 步骤 / 指标 | luminai M-Kiro/Antigravity | Aiide O-Max | 官方基准 | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 基本信息 | |||||||||||||||||||||||
| 服务名 | Claude Code | Claude Code | Claude Code | ||||||||||||||||||||
| 模型 | claude-haiku-4-5-20251001 | claude-haiku-4-5-20251001 | claude-haiku-4-5-20251001 | ||||||||||||||||||||
| 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 | 02:21:53 ~ 02:22:03 (5.3s) | 02:21:55 ~ 02:22:00 (4.5s) | 02:22:01 ~ 02:22:06 (2.9s) | ||||||||||||||||||||
| 提示词 | 查看本步 Promptping. Reply with the single word: pong | ||||||||||||||||||||||
| HTTP 头(TTFB) | 3,880 ms | 2,937 ms | 1,335 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 3,913 ms | 2,939 ms | 1,336 ms | ||||||||||||||||||||
| 总耗时 | 3,967 ms | 3,354 ms | 1,853 ms | ||||||||||||||||||||
| 输入 | 1,493 | 10 | 10 | ||||||||||||||||||||
| 输出 | 1 | 42 | 54 | ||||||||||||||||||||
| 缓存创建 | 2,059 5m: 2,059 / 1h: 0 | 21,545 5m: 0 / 1h: 21,545 | 6,166 5m: 0 / 1h: 6,166 | ||||||||||||||||||||
| 缓存读取 | 15,106 | 0 | 15,379 | ||||||||||||||||||||
| 输出速度 | - | 101.2 tok/s | 104.4 tok/s | ||||||||||||||||||||
| 响应 | pong | pong | pong | ||||||||||||||||||||
| 步骤 2: identity text | |||||||||||||||||||||||
| 时间 | 02:23:26 ~ 02:23:36 (5.5s) | 02:23:21 ~ 02:23:31 (6.3s) | 02:23:58 ~ 02:24:03 (4.8s) | ||||||||||||||||||||
| 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) | 3,643 ms | 2,828 ms | 1,598 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 3,645 ms | 2,829 ms | 1,599 ms | ||||||||||||||||||||
| 总耗时 | 4,122 ms | 5,250 ms | 3,809 ms | ||||||||||||||||||||
| 输入 | 1,509 | 10 | 10 | ||||||||||||||||||||
| 输出 | 28 | 197 | 193 | ||||||||||||||||||||
| 缓存创建 | 2,081 5m: 2,081 / 1h: 0 | 246 5m: 0 / 1h: 246 | 258 5m: 0 / 1h: 258 | ||||||||||||||||||||
| 缓存读取 | 15,263 | 21,545 | 21,545 | ||||||||||||||||||||
| 输出速度 | - | 81.4 tok/s | 87.3 tok/s | ||||||||||||||||||||
| 响应 | vendor: anthropic brand: claude model: claude-haiku-4-5-20251001 | 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 | 02:25:50 ~ 02:26:00 (5.0s) | 02:26:55 ~ 02:27:00 (4.4s) | 02:26:05 ~ 02:26:10 (3.5s) | ||||||||||||||||||||
| 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) | 3,937 ms | 2,656 ms | 1,869 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 3,939 ms | 2,660 ms | 1,870 ms | ||||||||||||||||||||
| 总耗时 | 3,989 ms | 3,436 ms | 2,533 ms | ||||||||||||||||||||
| 输入 | 1,514 | 10 | 10 | ||||||||||||||||||||
| 输出 | 4 | 66 | 71 | ||||||||||||||||||||
| 缓存创建 | 2,088 5m: 2,088 / 1h: 0 | 220 5m: 0 / 1h: 220 | 216 5m: 0 / 1h: 216 | ||||||||||||||||||||
| 缓存读取 | 15,320 | 21,791 | 21,803 | ||||||||||||||||||||
| 输出速度 | - | 85.1 tok/s | 107.1 tok/s | ||||||||||||||||||||
| 响应 | 2025-02 | 2025-02 | 2025-02 | ||||||||||||||||||||
| 步骤 4: identity_free text | |||||||||||||||||||||||
| 时间 | 02:29:16 ~ 02:29:26 (6.0s) | 02:29:21 ~ 02:29:31 (8.8s) | 02:29:44 ~ 02:29:55 (5.9s) | ||||||||||||||||||||
| 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) | 3,725 ms | 4,216 ms | 1,522 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 4,380 ms | 4,233 ms | 1,523 ms | ||||||||||||||||||||
| 总耗时 | 4,457 ms | 7,503 ms | 4,875 ms | ||||||||||||||||||||
| 输入 | 1,518 | 10 | 10 | ||||||||||||||||||||
| 输出 | 82 | 366 | 401 | ||||||||||||||||||||
| 缓存创建 | 2,094 5m: 2,094 / 1h: 0 | 106 5m: 0 / 1h: 106 | 113 5m: 0 / 1h: 113 | ||||||||||||||||||||
| 缓存读取 | 15,356 | 22,011 | 22,019 | ||||||||||||||||||||
| 输出速度 | - | 111.9 tok/s | 119.6 tok/s | ||||||||||||||||||||
| 响应 | 我是 Claude Haiku 4.5，由 Anthropic 开发的 AI 助手。我可以帮助软件工程任务、代码编写、文件编辑、命令执行和各类专业工作。我的目标是成为开发者的高效合作伙伴。 | 我是Claude Haiku 4.5，由Anthropic公司开发。属于Claude AI助手产品系列，是一个轻量级的大语言模型。 | 我是Claude Code，Anthropic公司开发的AI编程助手。我帮助用户解决软件工程任务，包括编写、调试、重构代码和实现新功能。 | ||||||||||||||||||||
| 步骤 5: knowledge_recall text | |||||||||||||||||||||||
| 时间 | 02:31:14 ~ 02:31:24 (5.1s) | 02:31:29 ~ 02:32:04 (34.7s) | 02:32:40 ~ 02:33:15 (32.0s) | ||||||||||||||||||||
| 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) | 2,963 ms | 2,523 ms | 1,740 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 2,964 ms | 2,527 ms | 1,742 ms | ||||||||||||||||||||
| 总耗时 | 3,965 ms | 33,697 ms | 31,012 ms | ||||||||||||||||||||
| 输入 | 658 | 10 | 10 | ||||||||||||||||||||
| 输出 | 192 | 3,527 | 3,174 | ||||||||||||||||||||
| 缓存创建 | 907 5m: 907 / 1h: 0 | 9,434 5m: 0 / 1h: 9,434 | 9,484 5m: 0 / 1h: 9,484 | ||||||||||||||||||||
| 缓存读取 | 6,657 | 0 | 0 | ||||||||||||||||||||
| 输出速度 | 191.8 tok/s | 113.2 tok/s | 108.4 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 | ```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 | ```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 | ||||||||||||||||||||
| 步骤 6: digit_count text | |||||||||||||||||||||||
| 时间 | 02:35:06 ~ 02:35:16 (6.3s) | 02:35:27 ~ 02:36:02 (31.8s) | 02:34:40 ~ 02:35:15 (30.2s) | ||||||||||||||||||||
| 提示词 | 查看本步 PromptCount digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=109327890466777644877450961969229780960550782759259699225713177559859883 | ||||||||||||||||||||||
| HTTP 头(TTFB) | 4,881 ms | 2,484 ms | 1,026 ms | ||||||||||||||||||||
| 首文本(SSE delta) | 4,882 ms | 2,495 ms | 1,028 ms | ||||||||||||||||||||
| 总耗时 | 5,128 ms | 30,503 ms | 29,260 ms | ||||||||||||||||||||
| 输入 | 189 | 193 | 193 | ||||||||||||||||||||
| 输出 | 19 | 3,489 | 3,600 | ||||||||||||||||||||
| 缓存创建 | - 5m: 0 / 1h: 0 | 0 5m: 0 / 1h: 0 | 0 5m: 0 / 1h: 0 | ||||||||||||||||||||
| 缓存读取 | - | 0 | 0 | ||||||||||||||||||||
| 输出速度 | - | 124.6 tok/s | 127.5 tok/s | ||||||||||||||||||||
| 响应 | ```json
{"n":72,"c":[8,8,8]}
```
| ```json
{"n":72,"c":[6,12,13]}
```
| ```json
{"n":72,"c":[6,12,13]}
```
| ||||||||||||||||||||
| 总计 | |||||||||||||||||||||||
| 总输入(含缓存) | 83,812 | 97,141 | 97,226 | ||||||||||||||||||||
| 总输出 | 326 | 7,687 | 7,493 | ||||||||||||||||||||
| 总缓存创建 | 9,229 5m: 9,229 / 1h: 0 | 31,551 5m: 0 / 1h: 31,551 | 16,237 5m: 0 / 1h: 16,237 | ||||||||||||||||||||
| 总缓存读取 | 67,702 | 65,347 | 80,746 | ||||||||||||||||||||
| 输出速度 | 191.8 tok/s | 116.4 tok/s | 116.6 tok/s | ||||||||||||||||||||
| 总执行时间 | 33.2s | 1m 30.5s | 1m 19.2s | ||||||||||||||||||||
| 总墙钟时间 | 13m 23.1s 含步骤间等待 | 14m 7.6s 含步骤间等待 | 13m 14.0s 含步骤间等待 | ||||||||||||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.0225 Anthropic: Claude Haiku 4.5 | $0.0847 Anthropic: Claude Haiku 4.5 | $0.0661 Anthropic: Claude Haiku 4.5 | ||||||||||||||||||||
| 通道指纹 | |||||||||||||||||||||||
| 来源步骤 | digit_count | digit_count | digit_count | ||||||||||||||||||||
| 平台 | one-api (100%) | one-api (100%) | direct (100%) | ||||||||||||||||||||
| 上游 | Anthropic 直连 (100%) | Anthropic 直连 (100%) | Anthropic 直连 (100%) | ||||||||||||||||||||
| CDN | cloudflare | cloudflare | - | ||||||||||||||||||||
| ID 格式 | msg_01GBgVcVUs89NWDzKxUDo24mhd | msg_01JuDrWEAgziHNYZNZhLnxkR | msg_01EpL4Zn6KFkuvJV2pH8n4zj | ||||||||||||||||||||
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 | 69 | 98 | 100 | ||||||||||||||||||||
| 基线状态 | 已对照基线 | 已对照基线 | 已对照基线 | ||||||||||||||||||||
| 缓存命中比 | 10.0 /10 ×20 | 10.0 /10 ×20 | 10.0 /10 ×20 | ||||||||||||||||||||
| 缓存 TTL 一致 | 0.0 /10 ×15 | 10.0 /10 ×15 | 10.0 /10 ×15 | ||||||||||||||||||||
| 延迟基线 | 7.0 /10 ×15 | 8.3 /10 ×15 | 10.0 /10 ×15 | ||||||||||||||||||||
| 模型匹配 | 10.0 /10 ×14 | 10.0 /10 ×14 | 10.0 /10 ×14 | ||||||||||||||||||||
| 缓存连续性 | 10.0 /10 ×14 | 10.0 /10 ×14 | 10.0 /10 ×14 | ||||||||||||||||||||
| sliding 5m | 10.0 /10 ×13 | 10.0 /10 ×13 | 10.0 /10 ×13 | ||||||||||||||||||||
| 原生 msg-ID | 10.0 /10 ×8 | 10.0 /10 ×8 | 10.0 /10 ×8 | ||||||||||||||||||||
| 系统提示纯净 | 0.0 /10 ×8 | 10.0 /10 ×8 | 10.0 /10 ×8 | ||||||||||||||||||||
| 身份(结构) | 10.0 /10 ×7 | 10.0 /10 ×7 | 10.0 /10 ×7 | ||||||||||||||||||||
| 身份(自由) | 10.0 /10 ×7 | 10.0 /10 ×7 | 10.0 /10 ×7 | ||||||||||||||||||||
| service_tier | 10.0 /10 ×6 | 10.0 /10 ×6 | 10.0 /10 ×6 | ||||||||||||||||||||
| 知识截止 | 10.0 /10 ×5 | 10.0 /10 ×5 | 10.0 /10 ×5 | ||||||||||||||||||||
| inference_geo | 0.0 /10 ×5 | 10.0 /10 ×5 | 10.0 /10 ×5 | ||||||||||||||||||||
| stop_reason | 10.0 /10 ×3 | 10.0 /10 ×3 | 10.0 /10 ×3 | ||||||||||||||||||||
| Req-ID 透传 | 0.0 /10 ×2 | 0.0 /10 ×2 | 10.0 /10 ×2 | ||||||||||||||||||||
| SDK 一致 | 10.0 /10 ×2 | 10.0 /10 ×2 | 10.0 /10 ×2 | ||||||||||||||||||||
| 流式投递 | 未计入 | 未计入 | 未计入 | ||||||||||||||||||||
| 综合结论 | |||||||||||||||||||||||
| 与基线相似度 | 69 v3.26.0 | 98 v3.26.0 | 基准（参考） | ||||||||||||||||||||
| 雷达图例 | 共 21 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 | 4271 ms | 13957 ms | 12224 ms | ||||||||||||||||||||
| 输出速度 | 191.8 tok/s | 116.4 tok/s | 116.6 tok/s | ||||||||||||||||||||
| 完成步骤 | 6/6 成功 | 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 ⓘ | $0.0225 | $0.0847 | $0.0661 | ||||||||||||||||||||
| 缓存读取占比 ⓘ | 81% | 67% | 83% | ||||||||||||||||||||
| 揭晓 | |||||||||||||||||||||||
| 通道 | 服务商 luminai ↗
通道M-Kiro/Antigravity | 服务商 Aiide ↗
通道O-Max | 官方基准 | ||||||||||||||||||||