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

2026/07/02 运行日期

claude-opus-4-8 官方基准

1 通道分数 < 70 另含 2 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

TopRouterCN / O-Max
```
评测失败
```

步骤 / 指标

SSSAiCode

R-Kiro

SSSAiCode

O-Max

ClaudeCN

O-Max

官方基准

基本信息

服务名 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

客户端 claude-cli v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195

偏差标红基于官方基准

步骤 1: ping text

时间 00:43:07 ~ 00:43:17 (5.4s) 00:43:13 ~ 00:43:18 (4.1s) 00:43:11 ~ 00:43:21 (6.2s) 00:43:15 ~ 00:43:25 (7.1s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,584 ms 2,319 ms 3,220 ms 3,631 ms

首文本(SSE delta) 2,621 ms 2,360 ms 3,223 ms 3,661 ms

总耗时 2,731 ms 2,825 ms 3,673 ms 3,962 ms

输入 0 2,300 2,326 2,326

输出 4 4 4 4

缓存创建

1,229

5m: 0 / 1h: 1,229

1,713

5m: 0 / 1h: 1,713

1,711

5m: 0 / 1h: 1,711

缓存读取 0 12,732 12,732 12,732

响应

pong

pong

pong

pong

步骤 2: identity text

时间 00:44:24 ~ 00:44:34 (5.8s) 00:45:16 ~ 00:45:26 (6.4s) 00:46:51 ~ 00:47:01 (6.7s) 00:46:38 ~ 00:46:48 (5.1s)

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) 3,967 ms 2,419 ms 4,355 ms 3,354 ms

首文本(SSE delta) 4,112 ms 5,208 ms 4,356 ms 3,355 ms

总耗时 4,311 ms 5,348 ms 4,770 ms 3,868 ms

输入 0 2 2 2

输出 26 216 28 28

缓存创建

2,489

5m: 0 / 1h: 2,489

2,515

5m: 0 / 1h: 2,515

2,515

5m: 0 / 1h: 2,515

缓存读取 0 13,961 14,445 14,443

输出速度 - burst - -

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

步骤 3: cutoff text

时间 00:47:06 ~ 00:47:11 (3.9s) 00:47:48 ~ 00:47:53 (3.4s) 00:48:31 ~ 00:48:36 (4.6s) 00:48:56 ~ 00:49:01 (3.2s)

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) 2,681 ms 2,350 ms 3,081 ms 1,833 ms

首文本(SSE delta) 2,711 ms 2,492 ms 3,082 ms 1,835 ms

总耗时 2,835 ms 2,571 ms 3,409 ms 2,133 ms

输入 0 2 2 2

输出 8 6 6 6

缓存创建

242

5m: 0 / 1h: 242

5m: 0 / 1h: 62

5m: 0 / 1h: 54

缓存读取 0 16,450 16,960 16,958

响应

2026-01

2025-03

2026-01

2026-01

步骤 4: identity_free text

时间 00:49:04 ~ 00:49:14 (5.3s) 00:51:31 ~ 00:51:36 (4.2s) 00:52:22 ~ 00:52:32 (7.4s) 00:50:18 ~ 00:50:23 (3.8s)

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) 3,989 ms 2,068 ms 4,640 ms 1,709 ms

首文本(SSE delta) 4,167 ms 3,182 ms 4,641 ms 1,711 ms

总耗时 4,497 ms 3,320 ms 6,263 ms 2,554 ms

输入 0 2 2 2

输出 51 75 59 56

缓存创建

5m: 0 / 1h: 39

5m: 0 / 1h: 35

缓存读取 0 16,692 17,022 17,012

输出速度 - - 36.4 tok/s 66.4 tok/s

响应

我是 Claude，由 Anthropic 打造的 AI 助手，在此作为 Claude Agent SDK 上的编程智能体，帮助完成软件工程任务。

我是 Claude，由 Anthropic 开发的 AI 助手。我可以帮你写代码、分析问题、处理文档和各类软件工程任务。当前基于 Claude Opus 4.8 模型。

我是 Claude，由 Anthropic 打造的 AI 助手。当前模型为 Claude Opus 4.8，可协助编程、写作、分析等任务。

我是 Claude，由 Anthropic 打造的 AI 助手。当前模型为 Opus 4.8，可用于编程等多种软件工程任务。

步骤 5: knowledge_recall text

时间 00:51:22 ~ 00:51:32 (9.4s) 00:54:52 ~ 00:55:02 (6.3s) 00:55:02 ~ 00:55:17 (11.3s) 00:53:05 ~ 00:53:20 (9.2s)

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) 5,159 ms 2,104 ms 3,287 ms 1,946 ms

首文本(SSE delta) 8,208 ms 2,609 ms 4,710 ms 3,353 ms

总耗时 8,636 ms 5,231 ms 9,458 ms 7,902 ms

输入 0 2 2 2

输出 342 348 648 675

缓存创建

5,443

5m: 0 / 1h: 5,443

5,753

5m: 0 / 1h: 5,753

5,740

5m: 0 / 1h: 5,740

缓存读取 0 0 0 0

输出速度 burst 132.7 tok/s 136.5 tok/s 148.4 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

步骤 6: digit_count text

时间 00:53:03 ~ 00:53:18 (14.1s) 00:56:56 ~ 00:57:01 (1.3s) 00:58:30 ~ 00:58:35 (3.5s) 00:55:51 ~ 00:55:56 (4.1s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=588617297320449541355176849612825067496156784358245490391908751725018326

HTTP 头(TTFB) 5,035 ms - 1,952 ms 2,694 ms

首文本(SSE delta) 11,838 ms - 1,953 ms 2,696 ms

总耗时 11,985 ms - 2,498 ms 3,028 ms

输入 0 - 211 211

输出 20 - 19 19

缓存创建

5m: 0 / 1h: 0

缓存读取 0 - 0 0

响应

{"n":72,"c":[5,7,7]}

失败

评测失败

{"n":70,"c":[6,6,7]}

{"n":70,"c":[7,5,10]}

总计

总输入(含缓存)

71,585

仅前 6 步

73,782

73,745

总输出

451

649

仅前 6 步

764

788

总缓存创建

9,442

5m: 0 / 1h: 9,442

仅前 6 步

10,078

5m: 0 / 1h: 10,078

10,055

5m: 0 / 1h: 10,055

总缓存读取

59,835

仅前 6 步

61,159

61,145

输出速度

burst

132.7 tok/s

仅前 6 步

111.0 tok/s

135.6 tok/s

总执行时间

43.8s

25.6s

仅前 6 步

39.7s

32.6s

总墙钟时间

10m 10.8s

含步骤间等待

13m 48.0s

含步骤间等待

仅前 6 步

15m 24.1s

含步骤间等待

12m 41.4s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

>=$0.0113

Anthropic: Claude Opus 4.8 (成本不完整)

$0.1167

Anthropic: Claude Opus 4.8 (部分)

$0.1254

Anthropic: Claude Opus 4.8

$0.1258

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count knowledge_recall 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 - - cloudflare -

ID 格式 msg_f96560d97014405997ce982547e86ac3 msg_01LUNSpM5r2BTBhYFrC71LcK msg_01HR2Fsgoz2LLv7H2NL1radE msg_01GMkov2WCDgoNtnXPEFDCeW

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: 1422959c-cc43-4903-af66-4d620cb346da	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	1782924785366-4dspfikptv14a 1422959c-cc43-4903-af66-4d620cb346da
O-Max	cf-ray: a146ef674dab97ca-LAX server: Photon-Edge	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	1782924893210-taw58aaj2uriv req_011CcbgrbdLxxguRTTK4ffRd a146ef674dab97ca-LAX
O-Max	cf-ray: a146f4bb89d23751-AMS server: cloudflare x-oneapi-request-id: 20260702005831690454172JPCmvV44	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-oneapi-request-idhdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a146f4bb89d23751-AMS
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_011CcbgvzMSciH2Ye5jGnb9A

协议指纹评分（机器自动）

总分 / 100 51 97 100

基线状态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

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

延迟基线 10.0 /10 ×15 — 9.5 /10 ×15 10.0 /10 ×15

模型匹配 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

sliding 5m 5.0 /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

身份(结构) 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

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

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

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

流式投递 0.0 /10 ×5 — 5.6 /10 ×5 10.0 /10 ×5

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

Req-ID 透传 0.0 /10 ×2 — 0.0 /10 ×2 10.0 /10 ×2

SDK 一致 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 10.0 /10 ×8

综合结论

与基线相似度 51 v3.26.0 执行失败，不评分 97 v3.26.0 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 Thinking 体量 thinking_volume_match
13 缓存连续 cache_continuity_intra
14 知识召回 knowledge_recall_match
15 延迟基线 latency_baseline_match
16 原生 msg-ID anthropic_msg_id_format
17 Sliding 缓存 cache_sliding_correctness
18 结构化身份 identity_structured_match
19 信封自报一致 envelope_self_report_match
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 5833 ms 3859 ms 5012 ms 3908 ms

输出速度 burst 132.7 tok/s 111.0 tok/s 135.6 tok/s

完成步骤 6/6 成功 5/6 成功 · 1 失败 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 ⓘ

>=$0.0113 (成本不完整)

$0.1167 (部分)

$0.1254

$0.1258

缓存读取占比 ⓘ - 84% (部分) 83% 83%

揭晓

通道

服务商 SSSAiCode ↗

通道R-Kiro

服务商 SSSAiCode ↗

通道O-Max

服务商 ClaudeCN ↗

通道O-Max

官方基准

返回列表