模型对比 | RPDiag

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。

5 通道 · 5 步骤

2026/07/02 运行日期

gpt-5.5 官方基准

1 通道分数 < 70 与基线相似度

已揭晓揭晓进度

步骤 / 指标

luminai

M-Team/Plus/API

5Cookie

O-Pro

94lover

O-Plus/Pro

JuCodex

O-Pro

官方基准

基本信息

服务名 Codex Codex Codex Codex Codex

模型 gpt-5.5 gpt-5.5 gpt-5.5 gpt-5.5 gpt-5.5

客户端 codex_exec v0.139.0 codex_exec v0.139.0 codex_exec v0.139.0 codex_exec v0.139.0 codex_exec v0.139.0

偏差标红基于官方基准

步骤 1: ping text

时间 05:54:24 ~ 05:54:44 (17.1s) 05:54:22 ~ 05:54:42 (16.0s) 05:54:20 ~ 05:54:35 (14.7s) 05:54:26 ~ 05:54:41 (14.3s) 05:54:28 ~ 05:54:43 (12.8s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 5,740 ms 1,073 ms 1,390 ms 2,272 ms 1,000 ms

总耗时 6,134 ms 5,215 ms 2,812 ms 3,155 ms 2,081 ms

输入 1,548 8,204 8,235 8,204 8,204

输出 5 5 5 5 5

缓存读取 8,576 1,920 1,920 1,920 1,920

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 05:55:03 ~ 05:55:18 (14.8s) 05:55:14 ~ 05:55:29 (13.9s) 05:55:07 ~ 05:55:22 (13.8s) 05:55:19 ~ 05:55:40 (17.3s) 05:55:01 ~ 05:55:21 (15.0s)

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) 3,527 ms 1,120 ms 1,171 ms 3,062 ms 823 ms

总耗时 3,920 ms 2,382 ms 2,895 ms 4,276 ms 3,336 ms

输入 148 148 179 148 8,340

输出 20 23 20 23 23

缓存读取 10,112 10,112 10,112 10,112 1,920

响应

vendor: openai
brand: codex
model: gpt-5

vendor: openai
brand: codex
model: gpt-5-codex

vendor: openai
brand: codex
model: gpt-5

vendor: openai
brand: codex
model: gpt-5-codex

vendor: openai
brand: codex
model: gpt-5-codex

步骤 3: cutoff text

时间 05:55:54 ~ 05:56:15 (15.2s) 05:56:11 ~ 05:56:31 (16.3s) 05:55:52 ~ 05:56:07 (13.9s) 05:56:16 ~ 05:56:31 (14.9s) 05:56:06 ~ 05:56:21 (14.0s)

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) 3,763 ms 3,460 ms 1,417 ms 2,488 ms 835 ms

总耗时 4,187 ms 4,461 ms 2,604 ms 3,458 ms 1,758 ms

输入 194 197 225 8,389 195

输出 8 8 8 8 8

缓存读取 10,112 10,112 10,112 1,920 10,112

响应

2024-06

2024-06

2024-06

2024-06

2024-06

步骤 4: identity_free text

时间 05:56:58 ~ 05:57:18 (17.1s) 05:57:08 ~ 05:57:23 (14.0s) 05:56:39 ~ 05:56:54 (13.9s) 05:57:00 ~ 05:57:20 (15.8s) 05:56:56 ~ 05:57:11 (14.6s)

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) 4,173 ms 790 ms - - 813 ms

总耗时 4,870 ms 1,899 ms - - 2,628 ms

输入 226 228 - - 224

输出 35 21 - - 27

缓存读取 10,112 10,112 - - 10,112

输出速度 50.2 tok/s - - - -

响应

我是 OpenAI 开发的 Codex 编程助手，基于 GPT-5，用于协助代码理解、修改、调试与开发。

我是 Codex，属于 OpenAI 的编码助手产品，由 OpenAI 开发。

我是 OpenAI 开发的 Codex 编程助手，可协助阅读、修改、调试代码并完成工程任务。

我是 Codex，OpenAI 开发的编程助手，可协助阅读代码、修改项目、调试并验证实现。

我是 OpenAI 开发的 AI 助手，可帮助回答问题、分析信息和处理编程任务。

步骤 5: knowledge_recall text

时间 05:57:33 ~ 05:57:58 (22.2s) 05:57:45 ~ 05:58:05 (15.1s) 05:57:29 ~ 05:57:54 (24.8s) 05:57:43 ~ 05:58:08 (22.4s) 05:57:47 ~ 05:58:07 (15.4s)

提示词

查看本步 Prompt

Answer 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) 3,769 ms 835 ms 6,620 ms 2,496 ms 847 ms

总耗时 11,360 ms 4,394 ms 13,443 ms 11,661 ms 4,599 ms

输入 8,126 8,126 8,157 8,126 8,126

输出 170 170 182 459 174

缓存读取 0 0 0 0 0

输出速度 22.4 tok/s 47.8 tok/s 26.7 tok/s 50.1 tok/s 46.4 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

{"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

{"facts":{"super_bowl_lviii":"Kansas City Chiefs","oscars2024_best_picture":"Oppenheimer","ucl_2024":"Real Madrid","nba_2024":"Boston Celtics","copa_america_2024":"UNKNOWN","euro2024":"UNKNOWN","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

总计

总输入(含缓存) 49,154 49,159 38,940 38,819 49,153

总输出 238 227 215 495 237

总缓存创建 0 0 0 0 0

总缓存读取 38,912 32,256 22,144 13,952 24,064

输出速度 24.7 tok/s 47.8 tok/s 26.7 tok/s 50.1 tok/s 46.4 tok/s

总执行时间 1m 26.5s 1m 15.2s 1m 21.1s 1m 24.6s 1m 11.8s

总墙钟时间

3m 34.5s

含步骤间等待

3m 43.4s

含步骤间等待

3m 34.0s

含步骤间等待

3m 42.4s

含步骤间等待

3m 39.4s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.0778

OpenAI: GPT-5.5

$0.1075

OpenAI: GPT-5.5

$0.1015

OpenAI: GPT-5.5

$0.1462

OpenAI: GPT-5.5

$0.1446

OpenAI: GPT-5.5

通道指纹

来源步骤 knowledge_recall knowledge_recall knowledge_recall knowledge_recall knowledge_recall

平台 one-api (100%) one-api (100%) unknown (0%) one-api (100%) unknown (0%)

上游 - - - - -

CDN cloudflare - - cloudflare -

ID 格式 - - - - -

展开详细指纹（响应头 / body 特征 / 完整信号列表）

通道	response_headers_notable	response_body_traits	signals	request_id_chain
M-Team/Plus/API	cf-ray: a148aacbfd81d8cc-AMS server: cloudflare x-oneapi-request-id: 202607012157356944795758268d9d6yrFDtLvs	—	hdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-ray	a148aacbfd81d8cc-AMS
O-Pro	via: 1.1 Caddy x-oneapi-request-id: 202607012157463939145378268d9d63b32r6SD	via_chain: ["1.1 Caddy"]	hdr:x-oneapi-request-idhdr:via	—
O-Plus/Pro	server: nginx	—	—	e0a6b0ab-359c-4f28-97f0-fd5fbc6f4909
O-Pro	cf-ray: a148ab089b69917c-FRA server: cloudflare x-new-api-version: v0.0.0 x-oneapi-request-id: 20260701215745394653810rf6DL8Qv	—	hdr:x-new-api-versionhdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-ray	a148ab089b69917c-FRA
官方基准	server: nginx/1.22.1	—	—	—

协议指纹评分（机器自动）

总分 / 100 85 94 100 71 98

基线状态已对照基线已对照基线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 4.6 /10 ×20 10.0 /10 ×20

延迟基线 2.9 /10 ×15 8.3 /10 ×15 10.0 /10 ×15 5.0 /10 ×15 10.0 /10 ×15

模型匹配 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14

系统提示纯净 10.0 /10 ×8 10.0 /10 ×8 10.0 /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 10.0 /10 ×7 10.0 /10 ×7

身份(自由) 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7

知识截止 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

流式投递未计入未计入未计入未计入未计入

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 85 v3.26.0 94 v3.26.0 100 v3.26.0 71 v3.26.0 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

1 模型匹配 model_match
2 知识截止 cutoff_match
3 自由身份 identity_free_clean
4 系统提示纯净 system_prompt_clean
5 缓存命中比 cache_hit_ratio_match
6 知识召回 knowledge_recall_match
7 延迟基线 latency_baseline_match
8 结构化身份 identity_structured_match

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 6094 ms 3670 ms 4351 ms 4510 ms 2880 ms

输出速度 24.7 tok/s 47.8 tok/s 26.7 tok/s 50.1 tok/s 46.4 tok/s

完成步骤 5/5 成功 5/5 成功 5/5 成功 5/5 成功 5/5 成功

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.0778

$0.1075

$0.1015

$0.1462

$0.1446

缓存读取占比 ⓘ 79% 66% 57% 36% 49%

揭晓

通道

服务商 luminai ↗

通道M-Team/Plus/API

服务商 5Cookie ↗

通道O-Pro

服务商 94lover ↗

通道O-Plus/Pro

服务商 JuCodex ↗

通道O-Pro

官方基准

返回列表