模型对比 | RPDiag

测试说明点击展开 5 步 quick-probe-v1 详解

同一会话连续 5 步，覆盖 5 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。步与步之间随机延迟 1–4 分钟。第 3 步（cutoff）累计跨度 > 5 分钟保住 sliding cache 检测；全流程总跨度 > 6 分钟容纳新增的第 5 步。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。

4 通道 · 5 步骤

2026/06/16 运行日期

claude-sonnet-4-6 官方基准

2 通道分数 < 70 另含 1 任务失败

已揭晓揭晓进度

⚠ 1 通道不可测 · 已从主对比表移除点击展开原因

duckcoding / cc专用
```
评测失败
```

步骤 / 指标

HongMaCC

u-cc

AnyAIGC

M-

SSSAiCode

O-Max

官方基准

基本信息

服务名 Claude Code Claude Code Claude Code Claude Code

模型 claude-sonnet-4-6 claude-sonnet-4-6 claude-sonnet-4-6 claude-sonnet-4-6

客户端 claude-cli v2.1.160 claude-cli v2.1.160 claude-cli v2.1.160 claude-cli v2.1.160

偏差标红基于官方基准

步骤 1: ping text

时间 02:54:04 ~ 02:54:09 (3.6s) 02:54:00 ~ 02:54:10 (5.2s) 02:54:06 ~ 02:54:11 (3.3s) 02:54:08 ~ 02:54:13 (4.0s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,310 ms 3,478 ms 2,356 ms 2,872 ms

首文本(SSE delta) 2,311 ms 3,664 ms 2,430 ms 2,874 ms

总耗时 2,311 ms 3,740 ms 2,502 ms 2,980 ms

输入 0 1,136 3 3

输出 22 2 5 5

缓存创建

5m: 0 / 1h: 0

33,140

31,988

5m: 0 / 1h: 31,988

32,318

5m: 0 / 1h: 32,318

缓存读取 0 0 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 02:55:52 ~ 02:55:57 (4.6s) 02:57:50 ~ 02:58:00 (7.8s) 02:56:52 ~ 02:56:57 (3.6s) 02:55:15 ~ 02:55:20 (4.7s)

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) 2,951 ms 5,397 ms 2,081 ms 3,340 ms

首文本(SSE delta) 2,953 ms 5,596 ms 2,378 ms 3,342 ms

总耗时 2,953 ms 6,421 ms 2,442 ms 3,732 ms

输入 0 208 3 3

输出 190 16 22 22

缓存创建

5m: 0 / 1h: 0

1,133

189

5m: 0 / 1h: 189

189

5m: 0 / 1h: 189

缓存读取 0 33,140 31,988 32,318

输出速度 burst - - -

响应

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

vendor: anthropic
brand: claude
model: claude-sonnet-4-5

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

步骤 3: cutoff text

时间 02:59:28 ~ 02:59:33 (4.1s) 03:00:29 ~ 03:01:30 (57.6s) 02:58:03 ~ 02:58:08 (2.9s) 02:58:46 ~ 02:58:51 (4.1s)

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) 2,848 ms 56,379 ms 1,924 ms 2,967 ms

首文本(SSE delta) 2,849 ms 56,380 ms 2,028 ms 3,082 ms

总耗时 2,849 ms 56,437 ms 2,105 ms 3,155 ms

输入 0 8 3 3

输出 42 6 8 8

缓存创建

5m: 0 / 1h: 0

7,012

5m: 0 / 1h: 7,012

5m: 0 / 1h: 58

5m: 0 / 1h: 57

缓存读取 0 28,688 32,177 32,507

输出速度 burst - - -

响应

2025-08

2025-08

2025-04

2025-08

步骤 4: identity_free text

时间 03:02:05 ~ 03:02:16 (8.8s) 03:04:34 ~ 03:04:44 (5.0s) 03:00:16 ~ 03:00:21 (3.4s) 02:59:52 ~ 03:00:02 (5.0s)

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) 7,663 ms 3,257 ms 1,430 ms 3,446 ms

首文本(SSE delta) 7,664 ms 3,663 ms 2,662 ms 3,845 ms

总耗时 7,664 ms 3,675 ms 2,752 ms 4,049 ms

输入 0 8 3 3

输出 77 37 72 41

缓存创建

5m: 0 / 1h: 0

7,105

5m: 0 / 1h: 7,105

5m: 0 / 1h: 43

5m: 0 / 1h: 41

缓存读取 0 28,623 32,235 32,564

输出速度 burst burst - -

响应

我是Claude，Anthropic开发的AI助手。

我叫 Claude，是由 Anthropic 开发的 AI 助手，当前使用的模型版本为 claude-sonnet-4-6。

我是 Claude，由 Anthropic 开发的 AI 助手。我基于大型语言模型构建，旨在提供安全、有益的对话与任务辅助，包括写作、编程、分析等多种能力。

我叫 Claude，是由 Anthropic 开发的 AI 助手。当前版本为 Claude Sonnet 4.6。

步骤 5: knowledge_recall text

时间 03:05:31 ~ 03:05:41 (7.2s) 03:07:28 ~ 03:07:58 (25.5s) 03:04:19 ~ 03:04:29 (5.9s) 03:02:11 ~ 03:02:21 (5.0s)

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) 5,899 ms 3,283 ms 2,692 ms 2,121 ms

首文本(SSE delta) 5,900 ms 3,284 ms 5,006 ms 2,122 ms

总耗时 6,066 ms 24,217 ms 5,075 ms 3,930 ms

输入 0 8 3 3

输出 968 1,755 198 205

缓存创建

5m: 0 / 1h: 0

2,087

5m: 0 / 1h: 2,087

7,739

5m: 0 / 1h: 7,739

8,035

5m: 0 / 1h: 8,035

缓存读取 0 8,404 0 0

输出速度 burst 83.8 tok/s - 113.4 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":"Argentina","euro2024":"Spain","nobel

总计

总输入(含缓存) 0 150,700 136,432 138,044

总输出 1,299 1,816 305 281

总缓存创建

5m: 0 / 1h: 0

50,477

5m: 0 / 1h: 16,204

40,017

5m: 0 / 1h: 40,017

40,640

5m: 0 / 1h: 40,640

总缓存读取 0 98,855 96,400 97,389

输出速度 burst 83.8 tok/s - 113.4 tok/s

总执行时间 28.3s 1m 41.1s 19.2s 22.9s

总墙钟时间

11m 36.8s

含步骤间等待

13m 58.0s

含步骤间等待

10m 22.8s

含步骤间等待

8m 12.8s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

>=$0.0195

Anthropic: Claude Sonnet 4.6 (成本不完整)

$0.1218

Anthropic: Claude Sonnet 4.6

$0.1836

Anthropic: Claude Sonnet 4.6

$0.1859

Anthropic: Claude Sonnet 4.6

通道指纹

来源步骤 knowledge_recall knowledge_recall knowledge_recall knowledge_recall

平台 one-api (100%) direct (100%) direct (100%) direct (100%)

上游 Anthropic 直连 (100%) Anthropic 直连 (100%) Anthropic 直连 (100%) Anthropic 直连 (100%)

CDN - - - -

ID 格式 msg_ab789da947b81a6dfd41919c msg_mvBdQNgsuchMOng1l6929TGj msg_01DejTHmtr9yJjMVCASt9gvo msg_01Vno1huEfQJsbo6txruk19a

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
u-cc	server: nginx x-new-api-version: 1.0.10 x-oneapi-request-id: 202606151905324477724648268d9d6MHIBb22r	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: false usage_has_cache_fields: true	hdr:x-new-api-versionhdr:x-oneapi-request-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
M-	server: nginx	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: false usage_has_cache_fields: true	body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
O-Max	cf-ray: a0c3d7063e674383-LAX server: Photon-Edge set-cookie: _cfuvid=QkVQRn.82SYi4Gx3.3rO8A_B47ygiDIeiC6.6WHw2f0-1781550260.1982372-1.0.1.1-2F5v0l1GLOmwMzlyK5NllkoQ0W_G2dxwV25K0TBSaPA; HttpOnly; SameSite=None; Secure; Path=/; Domain=api.anthropic.com	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: false usage_has_cache_fields: true	body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	1781550260144-zop7o6p96qhwk req_011Cc5ZnUWRwSSa79nSnmDN3 a0c3d7063e674383-LAX
官方基准	server: nginx/1.22.1	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: false usage_has_cache_fields: true	body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_011Cc5Zd4v6qgXSLi2Xcnq4J

协议指纹评分（机器自动）

总分 / 100 61 77 93 100

基线状态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 0.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20

缓存 TTL 一致 0.0 /10 ×15 4.0 /10 ×15 10.0 /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

缓存连续性 5.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14

sliding 5m 5.0 /10 ×13 10.0 /10 ×13 10.0 /10 ×13 10.0 /10 ×13

原生 msg-ID 0.0 /10 ×8 0.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8

身份(结构) 10.0 /10 ×7 10.0 /10 ×7 6.7 /10 ×7 10.0 /10 ×7

知识截止 10.0 /10 ×7 10.0 /10 ×7 5.0 /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

service_tier 10.0 /10 ×6 4.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6

inference_geo 10.0 /10 ×5 4.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

延迟基线 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

Req-ID 透传 0.0 /10 ×4 0.0 /10 ×4 10.0 /10 ×4 10.0 /10 ×4

stop_reason 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3

SDK 一致 10.0 /10 ×2 10.0 /10 ×2 10.0 /10 ×2 10.0 /10 ×2

系统提示纯净未计入 0.0 /10 ×8 5.0 /10 ×8 10.0 /10 ×8

流式投递 — — — —

综合结论

与基线相似度 61 v3.16.0 77 v3.16.0 93 v3.16.0 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

1 模型匹配 model_match
2 知识截止 cutoff_match
3 SDK 一致 sdk_consistency
4 Thinking 存在 thinking_present
5 自由身份 identity_free_clean
6 停止原因 stop_reason_present
7 Service Tier service_tier_present
8 缓存命中比 cache_hit_ratio_match
9 缓存 TTL 一致 cache_ttl_consistency
10 推理地区 inference_geo_present
11 缓存连续 cache_continuity_intra
12 知识召回 knowledge_recall_match
13 延迟基线 latency_baseline_match
14 原生 msg-ID anthropic_msg_id_format
15 Sliding 缓存 cache_sliding_correctness
16 结构化身份 identity_structured_match
17 自报身份一致 self_identity_consistency
18 中文遵循 instruction_following_lang
19 Req-ID 透传 anthropic_request_id_passthrough

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 4369 ms 18898 ms 2975 ms 3569 ms

输出速度 burst 83.8 tok/s - 113.4 tok/s

完成步骤 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 ⓘ

>=$0.0195 (成本不完整)

$0.1218

$0.1836

$0.1859

缓存读取占比 ⓘ - 66% 71% 71%

揭晓

通道

服务商 HongMaCC ↗

通道u-cc

服务商 AnyAIGC ↗

通道M-

服务商 SSSAiCode ↗

通道O-Max

官方基准

返回列表