测试说明 点击展开 5 步 quick-probe-v1 详解
Codex/OpenAI 版快速探针：前 4 步同一会话，第 5 步（知识召回）独立新会话，覆盖服务无关的核心信号——
1. ping/pong —— 单字指令遵循 + 建立会话。
2. 身份（结构化）—— 三行 vendor / brand / model，机器可解析（期望按官方基线多数派 baseline-derived，不硬编码 OpenAI 身份）。
3. 知识截止 —— YYYY-MM 格式，与官方基线对照。
4. 身份（自由格式）—— 自然语言自报，给包装层暴露品牌的机会。
5. 知识召回 —— 工具禁用、独立新会话的参数化公共事实题。
codex 走 /responses wire：缓存 / Anthropic 信封 / extended-thinking 等维度对其 N/A（见 codex 评分 profile），故无需 claude 版的 5 分钟 sliding-cache 边界时序，步间仅轻量间隔避免限流。
1 通道 · 5 步骤
2026/07/03 运行日期
gpt-5.5 官方基准
3 任务失败 执行不完整
已揭晓 揭晓进度
3 通道不可测 · 已从主对比表移除 点击展开原因
- CCAPI / O-Api
上游连接中断（未取得可评分响应）
- FineCoding / O-Plus
上游连接中断（未取得可评分响应）
- OmniaKey / O-Pro
上游连接中断（未取得可评分响应）
| 步骤 / 指标 | 官方基准 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 基本信息 | |||||||||||
| 服务名 | Codex | ||||||||||
| 模型 | gpt-5.5 | ||||||||||
| 客户端 | codex_exec v0.139.0 | ||||||||||
| 偏差标红基于官方基准 | |||||||||||
| 步骤 1: ping text | |||||||||||
| 时间 | 21:45:58 ~ 21:51:33 (13.8s) | ||||||||||
| 提示词 | 查看本步 Promptping. Reply with the single word: pong | ||||||||||
| HTTP 头(TTFB) | 2,022 ms | ||||||||||
| 总耗时 | 3,154 ms | ||||||||||
| 输入 | 1,550 | ||||||||||
| 输出 | 5 | ||||||||||
| 缓存读取 | 8,576 | ||||||||||
| 响应 | pong | ||||||||||
| 步骤 2: identity text | |||||||||||
| 时间 | 21:51:58 ~ 21:52:13 (14.5s) | ||||||||||
| 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) | 824 ms | ||||||||||
| 总耗时 | 3,840 ms | ||||||||||
| 输入 | 159 | ||||||||||
| 输出 | 116 | ||||||||||
| 缓存读取 | 10,112 | ||||||||||
| 输出速度 | 38.5 tok/s | ||||||||||
| 响应 | vendor: openai brand: codex model: gpt-5 | ||||||||||
| 步骤 3: cutoff text | |||||||||||
| 时间 | 21:52:34 ~ 21:52:49 (13.4s) | ||||||||||
| 提示词 | 查看本步 PromptKnowledge cutoff date? Reply with YYYY-MM only. | ||||||||||
| HTTP 头(TTFB) | 974 ms | ||||||||||
| 总耗时 | 2,650 ms | ||||||||||
| 输入 | 195 | ||||||||||
| 输出 | 8 | ||||||||||
| 缓存读取 | 10,112 | ||||||||||
| 响应 | 2024-06 | ||||||||||
| 步骤 4: identity_free text | |||||||||||
| 时间 | 21:53:08 ~ 21:53:23 (13.0s) | ||||||||||
| 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) | 924 ms | ||||||||||
| 总耗时 | 2,321 ms | ||||||||||
| 输入 | 226 | ||||||||||
| 输出 | 25 | ||||||||||
| 缓存读取 | 10,112 | ||||||||||
| 响应 | 我叫 Codex，属于 OpenAI 的 Codex 编程助手产品，由 OpenAI 开发。 | ||||||||||
| 步骤 5: knowledge_recall text | |||||||||||
| 时间 | 21:53:40 ~ 21:54:00 (16.4s) | ||||||||||
| 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) | 805 ms | ||||||||||
| 总耗时 | 5,727 ms | ||||||||||
| 输入 | 8,128 | ||||||||||
| 输出 | 170 | ||||||||||
| 缓存读取 | 0 | ||||||||||
| 输出速度 | 34.5 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 | ||||||||||
| 总计 | |||||||||||
| 总输入(含缓存) | 49,170 | ||||||||||
| 总输出 | 324 | ||||||||||
| 总缓存创建 | 0 | ||||||||||
| 总缓存读取 | 38,912 | ||||||||||
| 输出速度 | 36.0 tok/s | ||||||||||
| 总执行时间 | 1m 11.1s | ||||||||||
| 总墙钟时间 | 8m 2.4s 含步骤间等待 | ||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.0805 OpenAI: GPT-5.5 | ||||||||||
| 通道指纹 | |||||||||||
| 来源步骤 | knowledge_recall | ||||||||||
| 平台 | unknown (0%) | ||||||||||
| 上游 | - | ||||||||||
| CDN | - | ||||||||||
| ID 格式 | - | ||||||||||
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 | 94 | ||||||||||
| 基线状态 | 已对照基线 | ||||||||||
| 缓存命中比 | 10.0 /10 ×20 | ||||||||||
| 延迟基线 | 10.0 /10 ×15 | ||||||||||
| 模型匹配 | 10.0 /10 ×14 | ||||||||||
| 系统提示纯净 | 10.0 /10 ×8 | ||||||||||
| 身份(结构) | 10.0 /10 ×7 | ||||||||||
| 身份(自由) | 10.0 /10 ×7 | ||||||||||
| 知识截止 | 10.0 /10 ×5 | ||||||||||
| 流式投递 | 未计入 | ||||||||||
| 另有 9 个维度不适用于本服务，已排除评分（不计入总分） | |||||||||||
| 综合结论 | |||||||||||
| 与基线相似度 | 基准（参考） | ||||||||||
| 雷达图例 | 共 8 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 | 3538 ms | ||||||||||
| 输出速度 | 36.0 tok/s | ||||||||||
| 完成步骤 | 5/5 成功 | ||||||||||
|
按官方价目重估
同等内容若直发 Anthropic 的估算 ⓘ | $0.0805 | ||||||||||
| 缓存读取占比 ⓘ | 79% | ||||||||||
| 揭晓 | |||||||||||
| 通道 | 官方基准 | ||||||||||