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

全部 ≥ 70 与基线相似度

已揭晓揭晓进度

步骤 / 指标

DoroAI

PackyCode

cx-Zeus

官方基准

RayinCode

O-Pro

WanmoAPI

O-Pro

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 06:51:44 ~ 06:51:59 (13.4s) 06:51:46 ~ 06:52:01 (12.9s) 06:51:48 ~ 06:52:03 (12.4s) 06:51:42 ~ 06:51:57 (13.5s) 06:51:40 ~ 06:52:00 (15.5s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 1,493 ms 1,091 ms 909 ms 1,461 ms 3,155 ms

总耗时 2,536 ms 2,029 ms 1,577 ms 2,545 ms 3,478 ms

输入 1,548 1,548 1,548 8,204 12

输出 5 5 5 5 5

缓存读取 8,576 8,576 8,576 1,920 10,112

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 06:52:34 ~ 06:52:54 (15.9s) 06:52:24 ~ 06:52:39 (12.8s) 06:52:41 ~ 06:53:01 (18.2s) 06:52:15 ~ 06:52:30 (12.7s) 06:52:27 ~ 06:52:42 (14.7s)

提示词

查看本步 Prompt

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。严格按以下 3 行格式输出，全部小写英文，不要任何其他文字、解释、标点：
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) 2,311 ms 1,080 ms 3,597 ms 1,012 ms 1,596 ms

总耗时 4,757 ms 2,073 ms 7,496 ms 2,126 ms 4,147 ms

输入 151 151 151 151 151

输出 23 20 127 20 135

缓存读取 10,112 10,112 10,112 10,112 10,112

输出速度 - - 32.6 tok/s - 52.9 tok/s

响应

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

vendor: openai
brand: codex
model: gpt-5

vendor: openai
brand: codex
model: gpt-5

vendor: openai
brand: codex
model: gpt-5

vendor: openai
brand: codex
model: gpt-5

步骤 3: cutoff text

时间 06:53:37 ~ 06:53:57 (16.0s) 06:53:16 ~ 06:53:31 (12.5s) 06:53:45 ~ 06:54:00 (12.4s) 06:52:58 ~ 06:53:13 (12.5s) 06:53:10 ~ 06:53:25 (12.7s)

提示词

查看本步 Prompt

请直接回答你的知识截止日期，格式 YYYY-MM，不要附加任何说明。

HTTP 头(TTFB) 2,630 ms 1,078 ms 893 ms 1,017 ms 1,756 ms

总耗时 5,056 ms 1,873 ms 1,689 ms 1,999 ms 2,057 ms

输入 198 8,389 1,723 195 197

输出 8 8 8 8 8

缓存读取 10,112 1,920 8,576 10,112 10,112

响应

2024-06

2024-06

2024-06

2024-06

2024-06

步骤 4: identity_free text

时间 06:54:18 ~ 06:54:34 (13.3s) 06:54:05 ~ 06:54:21 (12.6s) 06:54:32 ~ 06:54:47 (13.5s) 06:53:39 ~ 06:53:55 (13.2s) 06:54:07 ~ 06:54:23 (12.9s)

提示词

查看本步 Prompt

用中文说说你的身份：什么产品？由谁打造？50 字以内。

HTTP 头(TTFB) 1,701 ms 974 ms 902 ms - 1,680 ms

总耗时 2,656 ms 1,911 ms 2,531 ms - 2,335 ms

输入 230 229 219 - 8,418

输出 24 23 34 - 29

缓存读取 10,112 10,112 10,112 - 1,920

输出速度 - - 20.9 tok/s - -

响应

我是 Codex，OpenAI 打造的编程智能助手，基于 GPT-5。

我是 Codex，基于 GPT-5 的编程助手，由 OpenAI 打造。

我是 Codex，OpenAI 打造的编程智能体，基于 GPT-5，用于协助阅读、修改和验证代码。

我是 OpenAI 开发的 Codex，基于 GPT-5 的编程助手，可协助阅读、修改和调试代码。

我是 OpenAI 开发的 AI 助手 Codex，可协助编程、分析代码和解决技术问题。

步骤 5: knowledge_recall text

时间 06:55:10 ~ 06:55:40 (26.2s) 06:55:05 ~ 06:55:25 (15.6s) 06:55:02 ~ 06:55:22 (16.1s) 06:54:23 ~ 06:54:43 (16.0s) 06:54:53 ~ 06:55:13 (15.6s)

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) 1,234 ms 1,060 ms 906 ms 1,532 ms 1,627 ms

总耗时 15,598 ms 4,833 ms 5,366 ms 5,507 ms 4,993 ms

输入 2,494 8,126 446 8,126 8,126

输出 708 182 179 182 179

缓存读取 5,632 0 7,680 0 0

输出速度 49.3 tok/s 48.2 tok/s 40.1 tok/s 45.8 tok/s 53.2 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":"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

总计

总输入(含缓存) 49,165 49,163 49,143 38,820 49,160

总输出 768 238 353 215 356

总缓存创建 0 0 0 0 0

总缓存读取 44,544 30,720 45,056 22,144 32,256

输出速度 49.3 tok/s 48.2 tok/s 34.0 tok/s 45.8 tok/s 53.1 tok/s

总执行时间 1m 24.8s 1m 6.4s 1m 12.5s 1m 8.0s 1m 11.4s

总墙钟时间

3m 55.9s

含步骤间等待

3m 38.8s

含步骤间等待

3m 33.9s

含步骤间等待

3m 0.9s

含步骤间等待

3m 32.9s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.0684

OpenAI: GPT-5.5

$0.1147

OpenAI: GPT-5.5

$0.0536

OpenAI: GPT-5.5

$0.1009

OpenAI: GPT-5.5

$0.1113

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

上游 - - - - -

CDN cloudflare 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
cx	cf-ray: a148ff2cbd63db41-SIN server: cloudflare x-oneapi-request-id: 2026070122551168586198OwkibErf	—	hdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-ray	a148ff2cbd63db41-SIN
cx-Zeus	via: 1.1 Caddy cf-ray: a148ff0e0fe98901-LAX server: cloudflare x-oneapi-request-id: 20260702065506231951639z34CUN7i	via_chain: ["1.1 Caddy"]	hdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-rayhdr:via	a148ff0e0fe98901-LAX
官方基准	server: nginx/1.22.1	—	—	—
O-Pro	cf-ray: a148fe0649f0f908-SIN server: cloudflare	—	hdr:server:cloudflarehdr:cf-ray	7b2252aa-139c-4c59-a322-05a5ee5e42c4 a148fe0649f0f908-SIN
O-Pro	server: cdn x-new-api-version: sync-upstream-main-20260630-42a06689f305 x-oneapi-request-id: 202607012254539596807218268d9d6LXqKcZFF	—	hdr:x-new-api-versionhdr:x-oneapi-request-id	—

协议指纹评分（机器自动）

总分 / 100 98 100 100 100 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 10.0 /10 ×20 10.0 /10 ×20

延迟基线 8.9 /10 ×15 10.0 /10 ×15 10.0 /10 ×15 10.0 /10 ×15 8.6 /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 98 v3.26.0 100 v3.26.0 基准（参考） 100 v3.26.0 98 v3.26.0

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 6121 ms 2544 ms 3732 ms 2435 ms 3402 ms

输出速度 49.3 tok/s 48.2 tok/s 34.0 tok/s 45.8 tok/s 53.1 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 ⓘ

$0.0684

$0.1147

$0.0536

$0.1009

$0.1113

缓存读取占比 ⓘ 91% 62% 92% 57% 66%

揭晓

通道

服务商 DoroAI ↗

通道cx

服务商 PackyCode ↗

通道cx-Zeus

官方基准

服务商 RayinCode ↗

通道O-Pro

服务商 WanmoAPI ↗

通道O-Pro

返回列表