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 任务失败执行不完整

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

DawAPI / cc
```
评测失败
```

步骤 / 指标

duckcoding

cc专用

LinkAPI

O-Max

LingxiCode

M-

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 22:32:07 ~ 22:32:12 (4.4s) 22:32:09 ~ 22:32:19 (5.8s) 22:32:11 ~ 22:32:16 (4.7s) 22:32:13 ~ 22:32:18 (3.5s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,527 ms 4,226 ms 2,833 ms 2,243 ms

首文本(SSE delta) 2,529 ms 4,227 ms 2,834 ms 2,245 ms

总耗时 2,921 ms 4,461 ms 3,113 ms 2,384 ms

输入 1,454 2 1,454 1,454

输出 4 4 4 4

缓存创建

30,223

5m: 0 / 1h: 30,223

32,306

5m: 32,306 / 1h: 0

30,222

5m: 0 / 1h: 30,222

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 22:34:19 ~ 22:34:29 (6.7s) 22:35:56 ~ 22:36:01 (4.7s) 22:36:08 ~ 22:36:18 (5.8s) 22:34:46 ~ 22:34:51 (4.1s)

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。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) 2,972 ms 2,923 ms 4,542 ms 2,695 ms

首文本(SSE delta) 2,973 ms 2,924 ms 4,544 ms 2,698 ms

总耗时 5,590 ms 3,338 ms 4,653 ms 3,005 ms

输入 2 2 2 2

输出 28 28 28 28

缓存创建

1,634

5m: 0 / 1h: 1,634

3,724

5m: 3,724 / 1h: 0

1,634

5m: 0 / 1h: 1,634

1,634

5m: 0 / 1h: 1,634

缓存读取 30,223 28,764 30,222 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-4-8

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

步骤 3: cutoff text

时间 22:36:17 ~ 22:36:32 (10.6s) 22:38:00 ~ 22:38:05 (4.4s) 22:39:38 ~ 22:39:48 (5.7s) 22:38:44 ~ 22:38:49 (3.6s)

提示词

查看本步 Prompt

请用 YYYY-MM 格式告诉我你的训练数据截止日期，无需多余文字。

HTTP 头(TTFB) 6,514 ms 3,132 ms 4,238 ms 2,380 ms

首文本(SSE delta) 6,515 ms 3,133 ms 4,239 ms 2,382 ms

总耗时 9,648 ms 3,372 ms 4,514 ms 2,591 ms

输入 2 2 2 2

输出 6 6 6 6

缓存创建

5m: 0 / 1h: 65

3,793

5m: 3,793 / 1h: 0

5m: 0 / 1h: 54

5m: 0 / 1h: 71

缓存读取 31,857 28,764 31,856 31,856

响应

2026-01

2026-01

2025-01

2026-01

步骤 4: identity_free text

时间 22:40:21 ~ 22:40:32 (9.5s) 22:40:24 ~ 22:40:34 (5.0s) 22:43:38 ~ 22:43:48 (5.5s) 22:39:57 ~ 22:40:02 (4.3s)

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) 5,664 ms 3,302 ms 3,716 ms 2,379 ms

首文本(SSE delta) 5,665 ms 3,303 ms 3,717 ms 2,380 ms

总耗时 8,627 ms 3,886 ms 4,599 ms 3,307 ms

输入 2 2 2 2

输出 47 46 44 64

缓存创建

5m: 0 / 1h: 39

3,825

5m: 3,825 / 1h: 0

5m: 0 / 1h: 35

5m: 0 / 1h: 31

缓存读取 31,922 28,764 31,910 31,927

输出速度 15.9 tok/s 78.9 tok/s 49.9 tok/s 69.0 tok/s

响应

我是 Claude，由 Anthropic 开发的人工智能助手，能帮你处理编程、写作、分析等多种任务。

我是 Claude，一个由 Anthropic 开发的人工智能助手，基于 Claude Opus 4.8 模型。

我是 Claude，由 Anthropic 打造的 AI 助手，对应模型为 Claude Opus 4.8。

我是 Claude，一个由 Anthropic 开发的 AI 助手。当前模型是 Claude Opus 4.8，可以帮你完成编程、写作和各类任务。

步骤 5: knowledge_recall text

时间 22:42:13 ~ 22:42:28 (10.6s) 22:44:29 ~ 22:44:39 (9.6s) 22:45:59 ~ 22:46:14 (10.1s) 22:43:29 ~ 22:43:44 (10.0s)

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) 4,166 ms 3,268 ms 3,104 ms 2,307 ms

首文本(SSE delta) 7,466 ms 5,837 ms 6,975 ms 6,649 ms

总耗时 9,873 ms 8,388 ms 9,227 ms 9,027 ms

输入 2 2 2 2

输出 683 678 676 768

缓存创建

4,762

5m: 0 / 1h: 4,762

5,341

5m: 5,341 / 1h: 0

4,743

5m: 0 / 1h: 4,743

4,776

5m: 0 / 1h: 4,776

缓存读取 0 0 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

总计

总输入(含缓存) 132,187 135,291 132,138 132,201

总输出 768 762 758 870

总缓存创建

36,723

5m: 0 / 1h: 36,723

48,989

5m: 48,989 / 1h: 0

36,688

5m: 0 / 1h: 36,688

36,734

5m: 0 / 1h: 36,734

总缓存读取 94,002 86,292 93,988 94,005

输出速度 15.9 tok/s 78.9 tok/s 49.9 tok/s 69.0 tok/s

总执行时间 41.7s 29.5s 31.8s 25.5s

总墙钟时间

10m 20.8s

含步骤间等待

12m 29.8s

含步骤间等待

14m 2.8s

含步骤间等待

11m 30.8s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.3030

Anthropic: Claude Opus 4.8

$0.2536

Anthropic: Claude Opus 4.8

$0.3026

Anthropic: Claude Opus 4.8

$0.3056

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 knowledge_recall knowledge_recall knowledge_recall knowledge_recall

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

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

CDN - - cloudflare -

ID 格式 msg_01DuAjsHsN58rzN4My4u4iUy msg_01Sj78DVYSNkLUiuG8hLjfAa msg_01Nftijek8ynPEtKcgEEstpG msg_01XozHryRQC33JN23mKiAwRd

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
cc专用	server: Nginx x-oneapi-request-id: 202606151442144233052918268d9d6tvyS5VKs	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	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: 202606151444305169549848268d9d6OutqLCwB	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-	cf-ray: a0c25c9a2fa3fd4f-NRT server: cloudflare set-cookie: server_name_session=e44607f7628a2aebd93b10e6388b22e1; Max-Age=86400; httponly; path=/ x-oneapi-request-id: 20260615144600760684684CcQbCsS2	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	a0c25c9a2fa3fd4f-NRT
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_011Cc5Dts6pCukxn6R67znDh

协议指纹评分（机器自动）

总分 / 100 96 85 90 100

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

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

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

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

系统提示纯净 10.0 /10 ×8 5.0 /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 0.0 /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 10.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6

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

延迟基线 4.5 /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

流式投递 — — — —

综合结论

与基线相似度 96 v3.16.0 85 v3.16.0 90 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 系统提示纯净 system_prompt_clean
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 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 7332 ms 4689 ms 5221 ms 4063 ms

输出速度 15.9 tok/s 78.9 tok/s 49.9 tok/s 69.0 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 ⓘ

$0.3030

$0.2536

$0.3026

$0.3056

缓存读取占比 ⓘ 71% 64% 71% 71%

揭晓

通道

服务商 duckcoding ↗

通道cc专用

服务商 LinkAPI ↗

通道O-Max

服务商 LingxiCode ↗

通道M-

官方基准

返回列表