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。
2 通道 · 6 步骤
2026/07/04 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
- OmniaKey / O-Max
评测失败
- HongMaCC / u-cc
评测失败
| 步骤 / 指标 | FoxCode R-super | 官方基准 | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 基本信息 | |||||||||||||||||
| 服务名 | Claude Code | Claude Code | |||||||||||||||
| 模型 | claude-sonnet-4-6 | claude-sonnet-4-6 | |||||||||||||||
| 客户端 | 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 | 01:49:10 ~ 01:49:15 (4.6s) | 01:49:14 ~ 01:49:17 (2.5s) | |||||||||||||||
| 提示词 | 查看本步 Promptping. Reply with the single word: pong | ||||||||||||||||
| HTTP 头(TTFB) | 4,011 ms | 2,446 ms | |||||||||||||||
| 首文本(SSE delta) | 4,183 ms | 2,447 ms | |||||||||||||||
| 总耗时 | 4,557 ms | 2,528 ms | |||||||||||||||
| 输入 | 65 | 3 | |||||||||||||||
| 输出 | 12 | 5 | |||||||||||||||
| 缓存创建 | 22,761 5m: 22,761 / 1h: 0 | 6,217 5m: 0 / 1h: 6,217 | |||||||||||||||
| 缓存读取 | 0 | 16,046 | |||||||||||||||
| 响应 | pong | pong | |||||||||||||||
| 步骤 2: identity text | |||||||||||||||||
| 时间 | 01:52:50 ~ 01:52:54 (3.3s) | 01:50:48 ~ 01:50:50 (2.5s) | |||||||||||||||
| 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) | 2,083 ms | 2,235 ms | |||||||||||||||
| 首文本(SSE delta) | 2,084 ms | 2,236 ms | |||||||||||||||
| 总耗时 | 3,272 ms | 2,537 ms | |||||||||||||||
| 输入 | 65 | 3 | |||||||||||||||
| 输出 | 49 | 22 | |||||||||||||||
| 缓存创建 | 533 5m: 533 / 1h: 0 | 202 5m: 0 / 1h: 202 | |||||||||||||||
| 缓存读取 | 22,761 | 22,263 | |||||||||||||||
| 输出速度 | 41.2 tok/s | - | |||||||||||||||
| 响应 | vendor: anthropic brand: claude model: claude-sonnet-4-6 <thinking> Direct and accurate response provided. </thinking> | vendor: anthropic brand: claude model: claude-sonnet-4-6 | |||||||||||||||
| 步骤 3: cutoff text | |||||||||||||||||
| 时间 | 01:55:35 ~ 01:55:38 (2.5s) | 01:54:50 ~ 01:54:52 (2.1s) | |||||||||||||||
| 提示词 | 查看本步 PromptKnowledge cutoff date? Reply with YYYY-MM only. | ||||||||||||||||
| HTTP 头(TTFB) | 2,042 ms | 1,995 ms | |||||||||||||||
| 首文本(SSE delta) | 2,043 ms | 2,111 ms | |||||||||||||||
| 总耗时 | 2,548 ms | 2,127 ms | |||||||||||||||
| 输入 | 65 | 3 | |||||||||||||||
| 输出 | 17 | 8 | |||||||||||||||
| 缓存创建 | 354 5m: 354 / 1h: 0 | 55 5m: 0 / 1h: 55 | |||||||||||||||
| 缓存读取 | 23,294 | 22,465 | |||||||||||||||
| 响应 | 2025-08 | 2025-08 | |||||||||||||||
| 步骤 4: identity_free text | |||||||||||||||||
| 时间 | 01:58:13 ~ 01:58:17 (3.8s) | 01:55:58 ~ 01:56:01 (2.6s) | |||||||||||||||
| 提示词 | 查看本步 Prompt请用中文介绍你自己是什么产品或助手，由谁开发，50 字以内。 | ||||||||||||||||
| HTTP 头(TTFB) | 1,835 ms | 1,733 ms | |||||||||||||||
| 首文本(SSE delta) | 1,836 ms | 1,734 ms | |||||||||||||||
| 总耗时 | 3,820 ms | 2,562 ms | |||||||||||||||
| 输入 | 65 | 3 | |||||||||||||||
| 输出 | 99 | 64 | |||||||||||||||
| 缓存创建 | 367 5m: 367 / 1h: 0 | 43 5m: 0 / 1h: 43 | |||||||||||||||
| 缓存读取 | 23,648 | 22,520 | |||||||||||||||
| 输出速度 | 49.9 tok/s | 77.3 tok/s | |||||||||||||||
| 响应 | 我是 Claude，由 Anthropic 开发的 AI 助手。我能帮助编程、写作、分析和回答问题，致力于提供安全、有益的回应。 <thinking> That's about 48 characters, fits within the 50 character limit. </thinking> | 我是 Claude，由 Anthropic 开发的 AI 助手。我能帮助完成写作、分析、编程、问答等多种任务，致力于提供安全、有益的对话体验。 | |||||||||||||||
| 步骤 5: knowledge_recall text | |||||||||||||||||
| 时间 | 02:01:45 ~ 02:04:55 (189.5s) | 02:00:52 ~ 02:06:17 (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) | - | 1,437 ms | |||||||||||||||
| 首文本(SSE delta) | - | 1,438 ms | |||||||||||||||
| 总耗时 | - | 3,350 ms | |||||||||||||||
| 输入 | - | 3 | |||||||||||||||
| 输出 | - | 204 | |||||||||||||||
| 缓存创建 | - | 4,660 5m: 0 / 1h: 4,660 | |||||||||||||||
| 缓存读取 | - | 2,129 | |||||||||||||||
| 输出速度 | - | 106.7 tok/s | |||||||||||||||
| 响应 | 失败 评测失败 | {"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 | - | 02:08:46 ~ 02:09:01 (11.1s) | |||||||||||||||
| 提示词 | 查看本步 PromptCount digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=799291814118583054795313792841472663166137105702121052778396049425770221 | ||||||||||||||||
| HTTP 头(TTFB) | - | 1,554 ms | |||||||||||||||
| 首文本(SSE delta) | - | 1,555 ms | |||||||||||||||
| 总耗时 | - | 10,193 ms | |||||||||||||||
| 输入 | - | 164 | |||||||||||||||
| 输出 | - | 840 | |||||||||||||||
| 缓存创建 | - | 0 5m: 0 / 1h: 0 | |||||||||||||||
| 缓存读取 | - | 0 | |||||||||||||||
| 输出速度 | - | 97.2 tok/s | |||||||||||||||
| 响应 | 未执行 | ```json
{"n":72,"c":[6,10,7]}
```
**Verification walkthrough:**
```
s = 799291814118583054795313792841472663166137105702121052778396049425770221
^ | |||||||||||||||
| 总计 | |||||||||||||||||
| 总输入(含缓存) | 93,978 仅前 5 步 | 96,779 | |||||||||||||||
| 总输出 | 177 仅前 5 步 | 1,143 | |||||||||||||||
| 总缓存创建 | 24,015 5m: 24,015 / 1h: 0 仅前 5 步 | 11,177 5m: 0 / 1h: 11,177 | |||||||||||||||
| 总缓存读取 | 69,703 仅前 5 步 | 85,423 | |||||||||||||||
| 输出速度 | 46.7 tok/s 仅前 5 步 | 97.4 tok/s | |||||||||||||||
| 总执行时间 | 3m 23.7s 仅前 5 步 | 35.3s | |||||||||||||||
| 总墙钟时间 | 15m 45.3s 含步骤间等待 仅前 5 步 | 19m 46.6s 含步骤间等待 | |||||||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.0806 Anthropic: Claude Sonnet 4.6 (部分) | $0.0852 Anthropic: Claude Sonnet 4.6 | |||||||||||||||
| 通道指纹 | |||||||||||||||||
| 来源步骤 | identity_free | 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_01KXm6d7MJ0Oy22rucYTYQ3d | msg_011nJDrY4MJQ3YrUTD25ykCn | |||||||||||||||
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 | ||||||||||||||||
| 模型匹配 | — | 10.0 /10 ×14 | |||||||||||||||
| 缓存连续性 | — | 10.0 /10 ×14 | |||||||||||||||
| sliding 5m | — | 10.0 /10 ×13 | |||||||||||||||
| 缓存 TTL 一致 | — | 10.0 /10 ×15 | |||||||||||||||
| 缓存命中比 | — | 10.0 /10 ×20 | |||||||||||||||
| 身份(结构) | — | 10.0 /10 ×7 | |||||||||||||||
| 知识截止 | — | 10.0 /10 ×5 | |||||||||||||||
| 身份(自由) | — | 10.0 /10 ×7 | |||||||||||||||
| 原生 msg-ID | — | 10.0 /10 ×8 | |||||||||||||||
| Req-ID 透传 | — | 10.0 /10 ×2 | |||||||||||||||
| stop_reason | — | 10.0 /10 ×3 | |||||||||||||||
| service_tier | — | 10.0 /10 ×6 | |||||||||||||||
| inference_geo | — | 10.0 /10 ×5 | |||||||||||||||
| SDK 一致 | — | 10.0 /10 ×2 | |||||||||||||||
| 系统提示纯净 | — | 10.0 /10 ×8 | |||||||||||||||
| 延迟基线 | — | 10.0 /10 ×15 | |||||||||||||||
| 流式投递 | — | 未计入 | |||||||||||||||
| 综合结论 | |||||||||||||||||
| 与基线相似度 | 执行失败，不评分 | 基准（参考） | |||||||||||||||
| 雷达图例 | 共 19 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 | 3549 ms | 3883 ms | |||||||||||||||
| 输出速度 | 46.7 tok/s | 97.4 tok/s | |||||||||||||||
| 完成步骤 | 4/6 成功 · 1 失败 · 1 跳过 | 6/6 成功 | |||||||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.0806 (部分) | $0.0852 | |||||||||||||||
| 缓存读取占比 ⓘ | 74% (部分) | 88% | |||||||||||||||
| 揭晓 | |||||||||||||||||
| 通道 | 服务商 FoxCode ↗
通道R-super | 官方基准 | |||||||||||||||