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-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

TopRouterCN / O-Max
```
评测失败
```

步骤 / 指标

官方基准

ClaudeCN

O-Max

SudoCode

M-Max

ClaudeAPI

O-Bdrk

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 02:57:33 ~ 02:57:38 (3.2s) 02:57:31 ~ 02:57:36 (4.7s) 02:57:25 ~ 02:57:30 (3.6s) 02:57:29 ~ 02:57:34 (4.0s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,066 ms 3,154 ms 2,477 ms 2,242 ms

首文本(SSE delta) 2,068 ms 3,155 ms 2,479 ms 2,249 ms

总耗时 2,195 ms 3,369 ms 2,624 ms 2,651 ms

输入 1,454 1,454 1,454 1,454

输出 4 4 4 4

缓存创建

30,222

5m: 0 / 1h: 30,222

5m: 0 / 1h: 0

30,222

5m: 0 / 1h: 30,222

30,224

5m: 0 / 1h: 30,224

缓存读取 0 30,224 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 02:58:42 ~ 02:58:47 (3.1s) 02:59:15 ~ 02:59:25 (5.9s) 02:58:56 ~ 02:59:01 (3.4s) 02:59:53 ~ 02:59:58 (3.6s)

提示词

查看本步 Prompt

输出 3 行 metadata 描述你自己（当前 API 模型）。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。禁止任何额外字符：
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) 1,713 ms 4,042 ms 1,892 ms 1,778 ms

首文本(SSE delta) 1,714 ms 4,043 ms 1,893 ms 1,779 ms

总耗时 2,105 ms 4,599 ms 2,296 ms 2,350 ms

输入 2 2 2 2

输出 28 28 28 28

缓存创建

1,643

5m: 0 / 1h: 1,643

1,643

5m: 0 / 1h: 1,643

1,643

5m: 0 / 1h: 1,643

5m: 0 / 1h: 0

缓存读取 30,222 30,224 30,222 31,867

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 03:01:33 ~ 03:01:38 (3.1s) 03:02:17 ~ 03:02:57 (37.4s) 03:01:22 ~ 03:01:27 (3.1s) 03:02:46 ~ 03:02:51 (3.7s)

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) 1,763 ms 32,263 ms 1,917 ms 1,841 ms

首文本(SSE delta) 1,765 ms 35,987 ms 1,918 ms 1,842 ms

总耗时 1,998 ms 36,311 ms 2,128 ms 2,233 ms

输入 2 2 2 2

输出 6 6 6 6

缓存创建

5m: 0 / 1h: 62

5m: 0 / 1h: 64

5m: 0 / 1h: 62

缓存读取 31,865 31,867 31,865 31,867

响应

2026-01

2026-01

2026-01

2026-01

步骤 4: identity_free text

时间 03:03:48 ~ 03:03:53 (3.9s) 03:06:19 ~ 03:06:29 (6.3s) 03:02:36 ~ 03:02:41 (4.2s) 03:06:27 ~ 03:06:37 (5.6s)

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) 1,865 ms 4,251 ms 2,021 ms 2,545 ms

首文本(SSE delta) 1,867 ms 4,252 ms 2,024 ms 2,546 ms

总耗时 2,811 ms 5,227 ms 3,070 ms 3,616 ms

输入 2 2 2 2

输出 61 67 65 64

缓存创建

5m: 0 / 1h: 39

5m: 0 / 1h: 35

5m: 0 / 1h: 39

5m: 0 / 1h: 35

缓存读取 31,927 31,931 31,929 31,929

输出速度 64.6 tok/s 68.7 tok/s 62.1 tok/s 59.8 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手，基于 Claude Opus 4.8 模型，可协助编程、写作、分析等多种任务。

我是 Claude，由 Anthropic 打造的 AI 助手，当前模型为 Claude Opus 4.8，可通过 Claude Code 等工具协助编程与各类任务。

我是 Claude，由 Anthropic 开发的 AI 助手。我擅长编程、写作、分析和回答问题，致力于提供有帮助、诚实且安全的协助。

我是 Claude，由 Anthropic 打造的 AI 助手，当前模型为 Claude Opus 4.8，可通过 API 及 Claude Code 等工具使用。

步骤 5: knowledge_recall text

时间 03:07:14 ~ 03:07:24 (9.4s) 03:08:50 ~ 03:09:00 (9.4s) 03:06:21 ~ 03:06:31 (9.0s) 03:09:44 ~ 03:09:59 (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) 2,511 ms 2,660 ms 2,472 ms 3,280 ms

首文本(SSE delta) 5,940 ms 5,489 ms 5,368 ms 5,651 ms

总耗时 8,366 ms 8,259 ms 7,916 ms 8,587 ms

输入 2 2 2 2

输出 671 691 680 633

缓存创建

4,781

5m: 0 / 1h: 4,781

4,787

5m: 0 / 1h: 4,787

4,787

5m: 0 / 1h: 4,787

3,008

5m: 0 / 1h: 3,008

缓存读取 0 0 0 1,774

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

步骤 6: digit_count text

时间 03:09:52 ~ 03:09:57 (3.1s) 03:11:15 ~ 03:11:20 (4.0s) 03:09:09 ~ 03:09:14 (2.9s) 03:12:59 ~ 03:13:04 (3.6s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=231158084979454247828490917673770404114372446027005104146205240103105217

HTTP 头(TTFB) 1,276 ms 2,487 ms 1,545 ms 1,534 ms

首文本(SSE delta) 1,278 ms 2,488 ms 1,546 ms 1,535 ms

总耗时 2,029 ms 2,968 ms 1,937 ms 2,144 ms

输入 211 211 211 211

输出 19 19 19 19

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0

响应

{"n":72,"c":[10,7,5]}

{"n":72,"c":[12,7,5]}

{"n":72,"c":[10,7,4]}

{"n":72,"c":[11,7,6]}

总计

总输入(含缓存) 132,434 132,448 132,444 132,439

总输出 789 815 802 754

总缓存创建

36,747

5m: 0 / 1h: 36,747

6,529

5m: 0 / 1h: 6,529

36,755

5m: 0 / 1h: 36,755

33,329

5m: 0 / 1h: 33,329

总缓存读取 94,014 124,246 94,016 97,437

输出速度 64.6 tok/s 68.7 tok/s 62.1 tok/s 59.8 tok/s

总执行时间 25.8s 1m 7.6s 26.1s 30.4s

总墙钟时间

12m 23.9s

含步骤间等待

13m 49.0s

含步骤间等待

11m 48.9s

含步骤间等待

15m 34.9s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.3048

Anthropic: Claude Opus 4.8

$0.1317

Anthropic: Claude Opus 4.8

$0.3051

Anthropic: Claude Opus 4.8

$0.2842

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count digit_count digit_count digit_count

平台 direct (100%) one-api (100%) one-api (100%) one-api (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_01KyG9UxDNUNn8K5njPnaboG msg_01KvPw8hN7xRxjmdzB73WF7E msg_017WMznPXCqEwhsUetCDpBvf msg_0119B2LR1hwNUSVMTJah44TR

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
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_011CcD9Sh1w4FZ6jKN5MGUf9
O-Max	cf-ray: a0e4d6ae1b5d29c4-AMS server: cloudflare x-oneapi-request-id: 20260620031116723920428soLoqq7m	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	a0e4d6ae1b5d29c4-AMS
M-Max	server: nginx x-new-api-version: v0.0.0 x-oneapi-request-id: 2026062003091068760150CTkSxYee	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	—
O-Bdrk	x-new-api-version: v1.0.0-rc.11 x-oneapi-request-id: 202606191913005003842728268d9d6V7hxaQfh	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	—

协议指纹评分（机器自动）

总分 / 100 98 98 96 97

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 8.6 /10 ×20 10.0 /10 ×20 8.6 /10 ×20 9.5 /10 ×20

缓存 TTL 一致 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

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 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) 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 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 10.0 /10 ×4 0.0 /10 ×4 0.0 /10 ×4 0.0 /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

综合结论

与基线相似度基准（参考） 98 v3.24.0 96 v3.24.0 97 v3.24.0

雷达图例

共 22 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 系统提示纯净 system_prompt_clean
9 Service Tier service_tier_present
10 缓存命中比 cache_hit_ratio_match
11 缓存 TTL 一致 cache_ttl_consistency
12 推理地区 inference_geo_present
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 中文遵循 instruction_following_lang
21 档位思考量 tier_thinking_volume_match
22 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 3251 ms 10122 ms 3329 ms 3597 ms

输出速度 64.6 tok/s 68.7 tok/s 62.1 tok/s 59.8 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 ⓘ

$0.3048

$0.1317

$0.3051

$0.2842

缓存读取占比 ⓘ 71% 94% 71% 74%

揭晓

通道

官方基准

服务商 ClaudeCN ↗

通道O-Max

服务商 SudoCode ↗

通道M-Max

服务商 ClaudeAPI ↗

通道O-Bdrk

返回列表