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

2026/06/15 运行日期

claude-opus-4-8 官方基准

1 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

ByteCatCode

O-Max

SSSAiCode

O-Max-L2

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 v2.1.160 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 12:43:30 ~ 12:43:35 (2.9s) 12:43:32 ~ 12:43:37 (4.4s) 12:43:36 ~ 12:43:41 (3.0s) 12:43:38 ~ 12:43:43 (3.7s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 1,996 ms 2,495 ms 1,615 ms 2,558 ms

首文本(SSE delta) 2,032 ms - 1,682 ms 2,560 ms

总耗时 2,036 ms 2,851 ms 1,743 ms 2,703 ms

输入 0 1,454 1,428 1,454

输出 4 4 4 4

缓存创建

30,222

5m: 0 / 1h: 30,222

29,765

5m: 0 / 1h: 29,765

30,222

5m: 0 / 1h: 30,222

缓存读取 0 0 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 12:45:16 ~ 12:46:41 (80.3s) 12:46:29 ~ 12:46:39 (5.1s) 12:45:35 ~ 12:45:40 (2.9s) 12:45:05 ~ 12:45:10 (3.2s)

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。自报身份，输出严格遵守以下 3 行格式（不允许 markdown、代码块、额外文本）：
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) 79,376 ms 2,663 ms 1,646 ms 1,757 ms

首文本(SSE delta) 79,379 ms - 2,028 ms 1,759 ms

总耗时 79,527 ms 3,882 ms 2,098 ms 2,126 ms

输入 0 2 2 2

输出 26 28 30 28

缓存创建

1,646

5m: 0 / 1h: 1,646

1,620

5m: 0 / 1h: 1,620

1,646

5m: 0 / 1h: 1,646

缓存读取 0 30,222 29,765 30,222

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-4-20250514

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

步骤 3: cutoff text

时间 12:48:18 ~ 12:48:23 (2.4s) 12:49:58 ~ 12:50:08 (7.6s) 12:46:49 ~ 12:46:54 (3.6s) 12:47:17 ~ 12:47:22 (3.8s)

提示词

查看本步 Prompt

请回报你的 knowledge cutoff，只输出 YYYY-MM。

HTTP 头(TTFB) 1,709 ms 6,174 ms 2,561 ms 2,561 ms

首文本(SSE delta) 1,739 ms - 2,693 ms 2,562 ms

总耗时 1,743 ms 6,537 ms 2,840 ms 2,778 ms

输入 0 2 2 2

输出 8 6 6 6

缓存创建

5m: 0 / 1h: 57

5m: 0 / 1h: 66

5m: 0 / 1h: 56

缓存读取 0 31,868 31,385 31,868

响应

2026-01

2026-01

2025-01

2026-01

步骤 4: identity_free text

时间 12:50:07 ~ 12:50:12 (3.1s) 12:54:01 ~ 12:54:16 (14.0s) 12:50:12 ~ 12:50:17 (4.3s) 12:50:51 ~ 12:50:56 (4.3s)

提示词

查看本步 Prompt

中文回答：你叫什么、属于哪个产品、谁开发？50 字内。

HTTP 头(TTFB) 2,072 ms 6,777 ms 2,368 ms 2,008 ms

首文本(SSE delta) 2,074 ms - 3,399 ms 2,010 ms

总耗时 2,204 ms 11,707 ms 3,462 ms 3,316 ms

输入 0 2 2 2

输出 33 66 71 71

缓存创建

5m: 0 / 1h: 39

缓存读取 0 31,925 31,451 31,924

输出速度 - 13.4 tok/s - 54.4 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手，当前模型为 Claude Opus 4.8。

我是 Claude，由 Anthropic 开发的 AI 助手。我能帮助完成编程、写作、分析等多种任务，致力于提供有用、可靠且安全的协助。

我是 Claude，由 Anthropic 开发的人工智能助手。我可以帮助你完成编程、写作、分析、问答等多种任务，致力于提供安全、有用、诚实的协助。

我是 Claude，由 Anthropic 开发的 AI 助手，基于 Claude Opus 4.8 模型，可帮助完成编程、写作、分析等多种软件工程与日常任务。

步骤 5: knowledge_recall text

时间 12:51:27 ~ 12:51:37 (9.2s) 12:57:25 ~ 12:57:35 (8.9s) 12:53:38 ~ 12:53:48 (5.1s) 12:52:44 ~ 12:52:54 (8.8s)

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) 4,813 ms 1,749 ms 1,719 ms 2,211 ms

首文本(SSE delta) 8,252 ms - 4,262 ms 5,022 ms

总耗时 8,542 ms 7,730 ms 4,313 ms 7,551 ms

输入 0 2 2 2

输出 342 673 317 690

缓存创建

4,784

5m: 0 / 1h: 4,784

4,315

5m: 0 / 1h: 4,315

4,788

5m: 0 / 1h: 4,788

缓存读取 0 0 0 0

输出速度 - 112.5 tok/s 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

总计

总输入(含缓存) 0 132,225 129,842 132,227

总输出 413 777 428 799

总缓存创建

36,748

5m: 0 / 1h: 36,748

35,805

5m: 0 / 1h: 35,805

36,751

5m: 0 / 1h: 36,751

总缓存读取 0 94,015 92,601 94,014

输出速度 - 67.7 tok/s burst 54.4 tok/s

总执行时间 1m 37.9s 39.9s 18.9s 23.8s

总墙钟时间

8m 6.9s

含步骤间等待

14m 2.8s

含步骤间等待

10m 11.9s

含步骤间等待

9m 15.8s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

>=$0.0103

Anthropic: Claude Opus 4.8 (成本不完整)

$0.3034

Anthropic: Claude Opus 4.8

$0.2880

Anthropic: Claude Opus 4.8

$0.3040

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 knowledge_recall knowledge_recall knowledge_recall knowledge_recall

平台 direct (75%) one-api (100%) direct (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_a5a92d02b08a4120a58460668b191820 msg_017Ss3UAwekZNogA872f5kKz msg_01LdNNG8eLKb8bZXjJudiRAa msg_01Po7awMr7QxXmwWZvA7CaMg

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: f5e8694b-a261-4d8d-90a6-45129ac1d40f	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	1781499087939-s6u2ujjhje9nn f5e8694b-a261-4d8d-90a6-45129ac1d40f
O-Max	server: nginx/1.29.8 x-oneapi-request-id: 202606150457264627397898268d9d6MtvypRqO	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-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
O-Max-L2	cf-ray: a0bef8e6e8b2cb9e-LAX server: Photon-Edge set-cookie: _cfuvid=M9rHsBd2tGnsHmgUEtWwjcwLtPkP60uBv6MRycJKIeY-1781499219.032105-1.0.1.1-WbIfynK1i_kI94ZgtJILmnDL1EvPsMIgZHrR.GCiKx8; 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	1781499218982-ou4ujqx16akoi req_011Cc4Sv1aqJFTXS3mjF4oZa a0bef8e6e8b2cb9e-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_011Cc4Sr5KhYN2EYzZbw5Jrs

协议指纹评分（机器自动）

总分 / 100 45 92 93 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 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

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 6.7 /10 ×7 10.0 /10 ×7

知识截止 0.0 /10 ×7 0.0 /10 ×7 10.0 /10 ×7 0.0 /10 ×7

身份(自由) 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7

service_tier 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 7.0 /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 10.0 /10 ×8 5.0 /10 ×8 10.0 /10 ×8

流式投递 — — — —

综合结论

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

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 18810 ms 6541 ms 2891 ms 3695 ms

输出速度 - 67.7 tok/s burst 54.4 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 ⓘ

>=$0.0103 (成本不完整)

$0.3034

$0.2880

$0.3040

缓存读取占比 ⓘ - 71% 71% 71%

揭晓

通道

服务商 SSSAiCode ↗

通道R-Kiro

服务商 ByteCatCode ↗

通道O-Max

服务商 SSSAiCode ↗

通道O-Max-L2

官方基准

返回列表