模型对比 | RPDiag

测试说明点击展开 5 步 quick-probe-v1 详解

前 5 步同一会话，第 6 步独立新会话，覆盖 6 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。 6. 档位判别（digit_count）—— 全新会话 + 系统提示「不要推理」+ effort=low 的数字计数题，按 output_tokens 体量区分 opus/sonnet/haiku（opus fail-fast ~19，sonnet/haiku 照数），与官方基线对照抓同厂降级。前 5 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；总跨度 > 6 分钟。第 6 步是独立新会话（不复用前 5 轮上下文，否则 opus 不再 fail-fast）。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 · 6 步骤

2026/06/20 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

InfAI / R-Kiro
```
评测失败
```

步骤 / 指标

SSSAiCode

R-Kiro

ClaudeZZ

R-kiro

LinkAPI

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 15:44:21 ~ 15:44:26 (4.2s) 15:44:15 ~ 15:44:25 (7.1s) 15:44:17 ~ 15:44:22 (4.4s) 15:44:23 ~ 15:44:33 (6.1s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,609 ms 5,249 ms 2,814 ms 4,916 ms

首文本(SSE delta) 2,671 ms 5,251 ms 2,820 ms 4,918 ms

总耗时 2,754 ms 5,662 ms 3,001 ms 5,058 ms

输入 0 3 3 3

输出 2 5 5 5

缓存创建

21,985

5m: 0 / 1h: 21,985

31,628

5m: 31,628 / 1h: 0

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 15:45:49 ~ 15:45:54 (3.0s) 15:45:41 ~ 15:45:51 (6.5s) 15:46:35 ~ 15:46:40 (4.0s) 15:47:11 ~ 15:47:16 (3.6s)

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。请只输出以下 3 行内容（label 小写，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) 1,704 ms 4,638 ms 2,520 ms 2,316 ms

首文本(SSE delta) 1,717 ms 4,640 ms 2,534 ms 2,318 ms

总耗时 2,025 ms 5,356 ms 2,840 ms 2,586 ms

输入 0 3 3 3

输出 18 22 22 22

缓存创建

185

5m: 0 / 1h: 185

178

5m: 178 / 1h: 0

178

5m: 0 / 1h: 178

缓存读取 0 21,985 31,628 32,318

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-4-6

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

步骤 3: cutoff text

时间 15:48:32 ~ 15:48:47 (11.4s) 15:48:07 ~ 15:48:17 (5.7s) 15:49:51 ~ 15:49:56 (4.0s) 15:50:39 ~ 15:50:49 (5.0s)

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) 7,033 ms 4,170 ms 2,812 ms 3,487 ms

首文本(SSE delta) 7,265 ms 4,177 ms 2,813 ms 3,489 ms

总耗时 7,410 ms 4,831 ms 2,998 ms 3,994 ms

输入 0 3 3 3

输出 3 8 8 8

缓存创建

5m: 0 / 1h: 81

5m: 57 / 1h: 0

5m: 0 / 1h: 57

缓存读取 0 22,170 31,806 32,496

响应

2025-08

2025-08

2025-08

2025-08

步骤 4: identity_free text

时间 15:50:02 ~ 15:50:07 (4.2s) 15:52:09 ~ 15:52:19 (6.0s) 15:53:41 ~ 15:53:46 (4.8s) 15:52:31 ~ 15:52:36 (4.2s)

提示词

查看本步 Prompt

用中文回答：你是谁？由谁开发？50 字以内。

HTTP 头(TTFB) 1,763 ms 4,195 ms 2,914 ms 2,287 ms

首文本(SSE delta) 1,920 ms 4,199 ms 2,916 ms 2,289 ms

总耗时 2,912 ms 5,197 ms 3,703 ms 3,146 ms

输入 0 3 3 3

输出 30 39 49 57

缓存创建

5m: 0 / 1h: 51

5m: 43 / 1h: 0

5m: 0 / 1h: 39

缓存读取 0 22,251 31,863 32,553

输出速度 30.2 tok/s 39.1 tok/s 62.3 tok/s 66.5 tok/s

响应

我是Kiro，一个由Anthropic开发的AI驱动开发环境。我基于Claude模型构建，专注于帮助开发者完成软件工程任务。

我是 Claude，由 Anthropic 开发的 AI 助手，当前版本为 claude-sonnet-4-6。

我是 Claude，由 Anthropic 开发的 AI 助手。我能帮助你完成写作、分析、编程、问答等多种任务。

我是 Claude，由 Anthropic 公司打造的 AI 助手。当前版本为 Claude Sonnet 4.6，专为对话、编程、分析等任务设计。

步骤 5: knowledge_recall text

时间 15:52:47 ~ 15:52:52 (4.6s) 15:55:37 ~ 15:55:52 (10.4s) 15:57:21 ~ 15:57:31 (5.9s) 15:53:43 ~ 15:53:53 (9.9s)

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) 1,777 ms 7,791 ms 2,970 ms 6,610 ms

首文本(SSE delta) 1,818 ms 7,792 ms 2,977 ms 6,673 ms

总耗时 3,758 ms 9,584 ms 4,928 ms 8,737 ms

输入 0 3 3 3

输出 222 204 205 205

缓存创建

8,209

5m: 0 / 1h: 8,209

8,060

5m: 8,060 / 1h: 0

8,038

5m: 0 / 1h: 8,038

缓存读取 0 0 0 0

输出速度 114.4 tok/s 113.8 tok/s 105.1 tok/s 99.3 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

步骤 6: digit_count text

时间 15:54:52 ~ 15:55:12 (14.9s) 15:59:03 ~ 15:59:23 (17.6s) 15:59:20 ~ 15:59:41 (15.9s) 15:55:47 ~ 15:56:07 (15.8s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=041509724903313202827866014847771382362721508214905704806713666995458522

HTTP 头(TTFB) 1,593 ms 3,275 ms 1,019 ms 1,604 ms

首文本(SSE delta) 1,736 ms 4,002 ms 1,031 ms 1,605 ms

总耗时 14,180 ms 16,074 ms 14,897 ms 14,862 ms

输入 0 3 191 164

输出 753 1,292 1,195 1,171

缓存创建

3,822

5m: 0 / 1h: 3,822

5m: 0 / 1h: 0

缓存读取 0 2,136 0 0

输出速度 60.5 tok/s 107.0 tok/s 86.2 tok/s 88.3 tok/s

响应

```json
{"n":72,"c":[9,8,5]}
```

**s** = `041509724903313202827866014847771382362721508214905704806713666995458522`

**Length:** 72 characters

**Counting 0s** (indices 1,5,11,17,25,44,50,53,56): **9**

**Counting 7s** (indices 7,21,

{"n":72,"c":[9,8,5]}

```json
{"n":72,"c":[9,8,5]}
```

总计

总输入(含缓存) 0 102,893 135,469 138,176

总输出 1,028 1,570 1,484 1,468

总缓存创建

34,333

5m: 0 / 1h: 34,333

39,966

5m: 39,966 / 1h: 0

40,630

5m: 0 / 1h: 40,630

总缓存读取 0 68,542 95,297 97,367

输出速度 65.4 tok/s 103.3 tok/s 87.3 tok/s 88.6 tok/s

总执行时间 42.2s 53.3s 39.0s 44.6s

总墙钟时间

10m 51.0s

含步骤间等待

15m 8.0s

含步骤间等待

15m 24.0s

含步骤间等待

11m 44.9s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

>=$0.0154

Anthropic: Claude Sonnet 4.6 (成本不完整)

$0.1729

Anthropic: Claude Sonnet 4.6

$0.1451

Anthropic: Claude Sonnet 4.6

$0.2041

Anthropic: Claude Sonnet 4.6

通道指纹

来源步骤 digit_count digit_count digit_count digit_count

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

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

CDN - - - -

ID 格式 msg_3de077149c88461d9708dad7dbbf1122 msg_012JjJhq9hMkmvDLHAuejfYQ msg_01Vb9VfgkRVB5QaZaijW1UMx msg_0134HqLhcjUvUHmXDQzzNQrK

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: f85f3fa0-b868-4d47-8e91-22556f5b7c44	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	1781942092982-6ntrfljjfbpnr f85f3fa0-b868-4d47-8e91-22556f5b7c44
R-kiro	via: 1.1 google cf-ray: 33e82c16a203c802f7fba621d73f796d-IAD server: nginx	id_format: msg_prefix via_chain: ["1.1 google"] extra_fields: ["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_33e82c16a203c802f7fba621d73f796d 33e82c16a203c802f7fba621d73f796d-IAD
O-Max	server: nginx set-cookie: server_name_session=9a42ff809bdc7f49eaa4735d20f97eff; Max-Age=86400; httponly; path=/ x-new-api-version: v1.0.0-rc.11 x-oneapi-request-id: 202606200759219926285968268d9d67wq3awjt	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	—
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_011CcE9rHXiwQPde3ZGwnqii

协议指纹评分（机器自动）

总分 / 100 51 88 83 96

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 7.6 /10 ×20 8.3 /10 ×20 8.4 /10 ×20

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

知识截止 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7

身份(自由) 0.0 /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

inference_geo 0.0 /10 ×5 10.0 /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

流式投递 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 0.0 /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

综合结论

与基线相似度 51 v3.24.0 88 v3.24.0 83 v3.24.0 基准（参考）

雷达图例

共 21 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 流式投递 buffer_dump_match
6 自由身份 identity_free_clean
7 停止原因 stop_reason_present
8 Service Tier service_tier_present
9 缓存命中比 cache_hit_ratio_match
10 缓存 TTL 一致 cache_ttl_consistency
11 推理地区 inference_geo_present
12 缓存连续 cache_continuity_intra
13 知识召回 knowledge_recall_match
14 延迟基线 latency_baseline_match
15 原生 msg-ID anthropic_msg_id_format
16 Sliding 缓存 cache_sliding_correctness
17 结构化身份 identity_structured_match
18 信封自报一致 envelope_self_report_match
19 中文遵循 instruction_following_lang
20 档位思考量 tier_thinking_volume_match
21 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 5507 ms 7784 ms 5395 ms 6397 ms

输出速度 65.4 tok/s 103.3 tok/s 87.3 tok/s 88.6 tok/s

完成步骤 6/6 成功 6/6 成功 6/6 成功 6/6 成功

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

>=$0.0154 (成本不完整)

$0.1729

$0.1451

$0.2041

缓存读取占比 ⓘ - 67% 70% 70%

揭晓

通道

服务商 SSSAiCode ↗

通道R-Kiro

服务商 ClaudeZZ ↗

通道R-kiro

服务商 LinkAPI ↗

通道O-Max

官方基准

返回列表