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。

5 通道 · 5 步骤

2026/06/15 运行日期

claude-opus-4-8 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

SSSAiCode

R-Kiro

PackyCode

cc-Zeus

ClaudeZZ

R-kiro

官方基准

SSSAiCode

O-Max-L2

基本信息

服务名 Claude Code Claude Code Claude Code Claude Code Claude Code

模型 claude-opus-4-8 claude-opus-4-8 claude-opus-4-8 claude-opus-4-8 claude-opus-4-8

客户端 claude-cli v2.1.160 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 11:03:23 ~ 11:03:29 (4.4s) 11:03:11 ~ 11:03:16 (3.5s) 11:03:16 ~ 11:03:26 (6.7s) 11:03:29 ~ 11:03:45 (2.8s) 11:03:25 ~ 11:03:31 (3.1s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 3,560 ms 2,142 ms 4,707 ms 1,725 ms 1,990 ms

首文本(SSE delta) 3,657 ms 2,144 ms 4,714 ms 1,727 ms 2,059 ms

总耗时 3,660 ms 2,397 ms 5,494 ms 1,871 ms 2,135 ms

输入 0 1,454 2 1,454 1,428

输出 4 4 4 4 4

缓存创建

30,223

5m: 0 / 1h: 30,223

27,914

5m: 0 / 1h: 27,914

30,222

5m: 0 / 1h: 30,222

29,762

5m: 0 / 1h: 29,762

缓存读取 0 0 0 0 0

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 11:06:10 ~ 11:06:15 (3.3s) 11:05:40 ~ 11:05:45 (3.6s) 11:06:43 ~ 11:06:53 (6.0s) 11:05:53 ~ 11:06:13 (4.0s) 11:06:07 ~ 11:06:12 (4.5s)

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。请按下列 3 行格式精确填空作答（label 不变，值小写）：
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) 2,100 ms 2,106 ms 3,715 ms 2,339 ms 2,708 ms

首文本(SSE delta) 2,122 ms 2,107 ms 3,717 ms 2,341 ms 3,046 ms

总耗时 2,142 ms 2,567 ms 4,331 ms 2,622 ms 3,109 ms

输入 0 2 2 2 2

输出 26 28 28 28 30

缓存创建

1,634

5m: 0 / 1h: 1,634

194

5m: 0 / 1h: 194

1,634

5m: 0 / 1h: 1,634

1,608

5m: 0 / 1h: 1,608

缓存读取 0 30,223 27,914 30,222 29,762

响应

vendor: anthropic
brand: claude
model: claude-opus-4-8

vendor: anthropic
brand: claude
model: claude-opus-4-8

vendor: anthropic
brand: claude
model: claude-opus-4-8

vendor: anthropic
brand: claude
model: claude-opus-4-8

vendor: anthropic
brand: claude
model: claude-opus-4-20250514

步骤 3: cutoff text

时间 11:07:44 ~ 11:07:49 (3.0s) 11:08:06 ~ 11:08:16 (7.3s) 11:09:32 ~ 11:09:42 (6.4s) 11:09:10 ~ 11:09:15 (3.6s) 11:08:36 ~ 11:08:41 (3.4s)

提示词

查看本步 Prompt

训练数据截止月份是？只回 YYYY-MM。

HTTP 头(TTFB) 2,095 ms 5,947 ms 5,114 ms 2,346 ms 2,296 ms

首文本(SSE delta) 2,198 ms 5,948 ms 5,115 ms 2,348 ms 2,458 ms

总耗时 2,202 ms 6,289 ms 5,471 ms 2,557 ms 2,607 ms

输入 0 2 2 2 2

输出 8 6 96 6 6

缓存创建

5m: 0 / 1h: 54

5m: 0 / 1h: 89

5m: 0 / 1h: 54

5m: 0 / 1h: 56

缓存读取 0 31,857 28,108 31,856 31,370

响应

2026-01

2025-01

2025-03

2025-01

2025-01

步骤 4: identity_free text

时间 11:09:38 ~ 11:09:43 (3.1s) 11:10:00 ~ 11:10:15 (12.8s) 11:13:21 ~ 11:13:31 (6.3s) 11:11:19 ~ 11:11:24 (4.1s) 11:12:12 ~ 11:12:17 (3.1s)

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) 2,024 ms 10,548 ms 4,691 ms 1,810 ms 1,544 ms

首文本(SSE delta) 2,026 ms 10,557 ms 4,693 ms 1,811 ms 2,277 ms

总耗时 2,361 ms 11,582 ms 5,408 ms 2,941 ms 2,352 ms

输入 0 2 2 2 2

输出 37 63 62 68 54

缓存创建

5m: 0 / 1h: 35

144

5m: 0 / 1h: 144

5m: 0 / 1h: 31

5m: 0 / 1h: 35

缓存读取 0 31,911 28,197 31,910 31,426

输出速度 110.4 tok/s 61.5 tok/s 86.7 tok/s 60.2 tok/s -

响应

我是 Claude，由 Anthropic 开发的 AI 助手，可帮助完成编程、写作、分析等多种任务。

我是 Claude，由 Anthropic 公司打造的人工智能助手。当前模型为 Claude Opus 4.8，可用于编程、写作、分析等多种任务。

我是 Claude，由 Anthropic 开发的 AI 助手。当前以 Claude Code 命令行工具的形式为你提供编程与软件工程方面的协助。

我是 Claude，由 Anthropic 开发的人工智能助手。我的具体模型是 Claude Opus 4.8，可以帮助你完成编程、写作、分析等各类任务。

我是 Claude，由 Anthropic 公司打造的 AI 助手，基于 Claude Opus 模型,用于对话和协助各类任务。

步骤 5: knowledge_recall text

时间 11:10:50 ~ 11:11:00 (8.5s) 11:11:47 ~ 11:11:57 (6.7s) 11:14:53 ~ 11:15:08 (10.9s) 11:13:23 ~ 11:13:43 (8.1s) 11:14:23 ~ 11:14:28 (4.5s)

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) 4,824 ms 1,774 ms 3,957 ms 1,787 ms 1,117 ms

首文本(SSE delta) 7,388 ms 2,705 ms 7,723 ms 5,097 ms 3,689 ms

总耗时 7,796 ms 5,261 ms 10,099 ms 7,002 ms 3,751 ms

输入 0 2 2 2 2

输出 342 438 786 671 317

缓存创建

4,763

5m: 0 / 1h: 4,763

8,145

5m: 0 / 1h: 8,145

4,763

5m: 0 / 1h: 4,763

4,269

5m: 0 / 1h: 4,269

缓存读取 0 0 3,067 0 0

输出速度 - burst burst burst burst

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) 0 132,162 123,782 132,154 129,724

总输出 417 539 976 777 411

总缓存创建

36,709

5m: 0 / 1h: 36,709

36,486

5m: 0 / 1h: 36,486

36,704

5m: 0 / 1h: 36,704

35,730

5m: 0 / 1h: 35,730

总缓存读取 0 93,991 87,286 93,988 92,558

输出速度 110.4 tok/s 61.5 tok/s 86.7 tok/s 60.2 tok/s burst

总执行时间 22.3s 33.9s 36.3s 22.7s 18.5s

总墙钟时间

7m 36.7s

含步骤间等待

8m 46.7s

含步骤间等待

11m 52.2s

含步骤间等待

10m 13.5s

含步骤间等待

11m 2.5s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

>=$0.0104

Anthropic: Claude Opus 4.8 (成本不完整)

$0.2972

Anthropic: Claude Opus 4.8

$0.2961

Anthropic: Claude Opus 4.8

$0.3031

Anthropic: Claude Opus 4.8

$0.2870

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 knowledge_recall knowledge_recall knowledge_recall knowledge_recall knowledge_recall

平台 direct (75%) one-api (100%) direct (100%) direct (100%) direct (100%)

上游 Anthropic 直连 (75%) Anthropic 直连 (100%) Anthropic 直连 (100%) Anthropic 直连 (100%) Anthropic 直连 (100%)

CDN - cloudflare - - -

ID 格式 msg_159800eaa2774bf9849fa33c940d95ea msg_0153c5WJRrHbeuVriBmUoSDY msg_01VxPAjTotL8AKwsjqQnQiuk msg_01VQYt7zYUm6aV6nedtCV2mc msg_0186TNUJgEJZHvSedcEZr1Xe

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
R-Kiro	server: Photon-Edge x-amzn-requestid: 6c8e1f0e-3bbc-4796-a70d-04753d16e58a	id_format: msg_prefix has_service_tier: false has_inference_geo: false model_has_date_suffix: false usage_has_cache_fields: true	body:id:msg_prefixbody:usage.cache_fieldsupstream:x-amzn-requestidupstream:anthropic-direct-from-body	1781493051545-2l90ho64d5rg3 6c8e1f0e-3bbc-4796-a70d-04753d16e58a
cc-Zeus	via: 1.1 Caddy cf-ray: a0be63bdadddb6c9-LAX server: cloudflare x-oneapi-request-id: 20260615111149558820217VsUsyfKX	id_format: msg_prefix via_chain: ["1.1 Caddy"] extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: false usage_has_cache_fields: true	hdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-rayhdr:viabody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a0be63bdadddb6c9-LAX
R-kiro	via: 1.1 google cf-ray: 7e8f4b0fb7d25a01150d15d9b75ea006-IAD server: nginx	id_format: msg_prefix via_chain: ["1.1 google"] extra_fields: ["diagnostics","stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: false usage_has_cache_fields: true	hdr:viabody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_7e8f4b0fb7d25a01150d15d9b75ea006 7e8f4b0fb7d25a01150d15d9b75ea006-IAD
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_011Cc4KHJB8DbAfp7TyPb5Nr
O-Max-L2	cf-ray: a0be6785da59f7b1-LAX server: Photon-Edge set-cookie: _cfuvid=Da116y1XsXFDKaY.xoADvcgHCu.ZOXkme.Ba_6Gpga0-1781493264.3003306-1.0.1.1-ppiWs.ehuSMAsgq2aXqZ0ia7HJ_B_vhoE18N3DuYb5Y; 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	1781493264234-trfz62183dvq7 req_011Cc4KM4WxYZJjWk68jrded a0be6785da59f7b1-LAX

协议指纹评分（机器自动）

总分 / 100 45 97 92 100 93

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 0.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20

缓存 TTL 一致 0.0 /10 ×15 10.0 /10 ×15 10.0 /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 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 10.0 /10 ×14

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

原生 msg-ID 0.0 /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 6.7 /10 ×7

知识截止 0.0 /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

service_tier 0.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6

inference_geo 0.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

延迟基线 10.0 /10 ×5 7.5 /10 ×5 7.7 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

Req-ID 透传 0.0 /10 ×4 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 10.0 /10 ×3

SDK 一致 10.0 /10 ×2 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 10.0 /10 ×8 0.0 /10 ×8 10.0 /10 ×8 5.0 /10 ×8

流式投递 — — — — —

综合结论

与基线相似度 45 v3.16.0 97 v3.16.0 92 v3.16.0 基准（参考） 93 v3.16.0

雷达图例

共 18 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 中文遵循 instruction_following_lang
18 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 3632 ms 5619 ms 6161 ms 3399 ms 2791 ms

输出速度 110.4 tok/s 61.5 tok/s 86.7 tok/s 60.2 tok/s burst

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 ⓘ

>=$0.0104 (成本不完整)

$0.2972

$0.2961

$0.3031

$0.2870

缓存读取占比 ⓘ - 71% 71% 71% 71%

揭晓

通道

服务商 SSSAiCode ↗

通道R-Kiro

服务商 PackyCode ↗

通道cc-Zeus

服务商 ClaudeZZ ↗

通道R-kiro

官方基准

服务商 SSSAiCode ↗

通道O-Max-L2

返回列表