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

2026/06/24 运行日期

claude-sonnet-4-6 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

Aiberm / cc
```
评测失败
```

步骤 / 指标

官方基准

Aiide

O-Max

TopRouterCN

O-Max

LingxiCode

M-

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 00:00:25 ~ 00:00:35 (5.2s) 00:00:23 ~ 00:00:53 (28.2s) 00:00:17 ~ 00:00:27 (9.4s) 00:00:21 ~ 00:00:31 (6.4s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 3,317 ms 25,830 ms 8,325 ms 4,442 ms

首文本(SSE delta) 3,319 ms 26,002 ms 8,332 ms 4,445 ms

总耗时 3,440 ms 26,658 ms 8,397 ms 4,622 ms

输入 3 3 1,467 3

输出 5 5 5 5

缓存创建

32,318

5m: 0 / 1h: 32,318

32,457

5m: 0 / 1h: 32,457

30,854

5m: 0 / 1h: 30,854

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 00:03:45 ~ 00:03:50 (3.3s) 00:03:09 ~ 00:03:14 (4.7s) 00:03:14 ~ 00:03:24 (9.3s) 00:03:05 ~ 00:03:10 (4.1s)

提示词

查看本步 Prompt

以下是对你自身的 metadata 探针。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。按以下 3 行回答自己的身份，每行一个 label，不要寒暄不要解释：
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) 1,837 ms 3,254 ms 8,413 ms 2,744 ms

首文本(SSE delta) 1,839 ms 3,255 ms 8,414 ms 2,745 ms

总耗时 2,277 ms 3,551 ms 8,505 ms 3,109 ms

输入 3 3 3 3

输出 22 22 22 22

缓存创建

202

5m: 0 / 1h: 202

202

5m: 0 / 1h: 202

1,666

5m: 0 / 1h: 1,666

202

5m: 0 / 1h: 202

缓存读取 32,318 32,457 30,854 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 00:06:59 ~ 00:07:04 (4.3s) 00:04:27 ~ 00:04:37 (5.4s) 00:07:02 ~ 00:07:12 (8.8s) 00:06:48 ~ 00:06:58 (7.8s)

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) 3,178 ms 3,193 ms 7,769 ms 5,879 ms

首文本(SSE delta) 3,180 ms 3,194 ms 7,771 ms 5,880 ms

总耗时 3,328 ms 3,391 ms 7,911 ms 6,539 ms

输入 3 3 3 3

输出 8 8 8 8

缓存创建

5m: 0 / 1h: 57

5m: 0 / 1h: 55

5m: 0 / 1h: 38

缓存读取 32,520 32,659 32,520 32,520

响应

2025-08

2025-08

2025-08

2025-08

步骤 4: identity_free text

时间 00:08:30 ~ 00:08:35 (3.2s) 00:05:42 ~ 00:05:52 (6.0s) 00:09:33 ~ 00:09:43 (5.2s) 00:09:05 ~ 00:09:15 (5.5s)

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) 1,996 ms 3,873 ms 4,358 ms 3,401 ms

首文本(SSE delta) 1,997 ms 3,875 ms 4,359 ms 3,405 ms

总耗时 2,237 ms 4,717 ms 4,451 ms 4,613 ms

输入 3 3 3 3

输出 24 54 41 69

缓存创建

5m: 0 / 1h: 35

5m: 0 / 1h: 43

5m: 0 / 1h: 41

5m: 0 / 1h: 43

缓存读取 32,577 32,714 32,558 32,558

输出速度 - 64.1 tok/s - 57.1 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手。

我是 Claude，由 Anthropic 开发的 AI 助手。我能帮助回答问题、编写代码、分析文本、创作内容等多种任务。

我叫 Claude，是由 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。我被设计为安全、有帮助且诚实的对话助手，能够协助完成写作、分析、编程、问答等多种任务。

步骤 5: knowledge_recall text

时间 00:12:06 ~ 00:12:16 (6.1s) 00:09:42 ~ 00:09:52 (7.8s) 00:12:03 ~ 00:12:13 (7.9s) 00:10:59 ~ 00:11:09 (6.4s)

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) 2,302 ms 4,072 ms 7,113 ms 2,844 ms

首文本(SSE delta) 2,304 ms 4,073 ms 7,115 ms 2,845 ms

总耗时 4,713 ms 6,570 ms 7,167 ms 5,474 ms

输入 3 3 3 3

输出 205 204 205 204

缓存创建

8,025

5m: 0 / 1h: 8,025

8,061

5m: 0 / 1h: 8,061

8,029

5m: 0 / 1h: 8,029

8,059

5m: 0 / 1h: 8,059

缓存读取 0 0 0 0

输出速度 85.1 tok/s 81.7 tok/s burst 77.6 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 00:13:34 ~ 00:13:54 (16.9s) 00:12:46 ~ 00:13:06 (19.8s) 00:15:01 ~ 00:15:26 (20.9s) 00:12:20 ~ 00:12:40 (15.9s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=492804223650834426324131342060732574480688514645578209047488104564256659

HTTP 头(TTFB) 1,040 ms 2,734 ms 6,687 ms 1,708 ms

首文本(SSE delta) 1,042 ms 2,949 ms 6,688 ms 1,709 ms

总耗时 15,894 ms 18,810 ms 20,134 ms 14,866 ms

输入 164 164 164 164

输出 961 1,200 1,925 919

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0

输出速度 64.7 tok/s 75.7 tok/s 143.2 tok/s 69.8 tok/s

响应

**Step 1 — Lay out the string in groups of 10:**

```
4928042236  (pos 1–10)
5083442632  (pos 11–20)
4131342060  (pos 21–30)
7325744806  (pos 31–40)
8851464557  (pos 41–50)
8209047488  (pos 51–60)
104

## Counting digits in `s`

**s** = `492804223650834426324131342060732574480688514645578209047488104564256659`

### Length
Grouping in 4s: `4928 0422 3650 8344 2632 4131 3420 6073 2574 4806 8851 4645 5

```
s = "492804223650834426324131342060732574480688514645578209047488104564256659"
```

**Digit-by-digit mapping (0-indexed):**

| idx | digit | idx | digit | idx | digit | idx | digit |
|-----|------

## Counting digits in `s`

**String:** `492804223650834426324131342060732574480688514645578209047488104564256659`

### Length
Counting all characters: **n = 72**

### Digit-by-digit scan

| Digit | Po

总计

总输入(含缓存) 138,231 138,827 138,203 138,235

总输出 1,225 1,493 2,206 1,227

总缓存创建

40,637

5m: 0 / 1h: 40,637

40,818

5m: 0 / 1h: 40,818

40,628

5m: 0 / 1h: 40,628

40,660

5m: 0 / 1h: 40,660

总缓存读取 97,415 97,830 95,932 97,396

输出速度 67.6 tok/s 75.9 tok/s 143.2 tok/s 70.1 tok/s

总执行时间 39.0s 1m 12.0s 1m 1.6s 46.1s

总墙钟时间

13m 28.9s

含步骤间等待

12m 43.0s

含步骤间等待

15m 9.1s

含步骤间等待

12m 19.0s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.2005

Anthropic: Claude Sonnet 4.6

$0.2053

Anthropic: Claude Sonnet 4.6

$0.2192

Anthropic: Claude Sonnet 4.6

$0.2006

Anthropic: Claude Sonnet 4.6

通道指纹

来源步骤 digit_count digit_count digit_count digit_count

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

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

CDN - cloudflare - cloudflare

ID 格式 msg_01CFrzVWfHw25EBgv6f7bxQm msg_01DT8zmuau2u15xG6gHdysoZ msg_01Wvf1yciDJCd1sivKpwXPXP msg_01N73ieRgm6AVWqewuFKMR9F

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_011CcLVEdQAcpn16xdPWZrfw
O-Max	cf-ray: a104c6be6d4666dc-AMS server: cloudflare x-new-api-version: 0.12.11 x-oneapi-request-id: 202606231612479748560178268d9d6cPjdOkk4	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-idhdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a104c6be6d4666dc-AMS
O-Max	server: nginx/1.27.5	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	tr-ew7y4grd-tlfecbjbfy-112602
M-	cf-ray: a104c61b799dfd4f-NRT server: cloudflare set-cookie: server_name_session=56fb82d09f6cfa691ede7bc922d16f50; Max-Age=86400; httponly; path=/ x-oneapi-request-id: 20260623161221810787583SQSnincH	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	a104c61b799dfd4f-NRT

协议指纹评分（机器自动）

总分 / 100 100 98 94 98

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 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 7.2 /10 ×5 10.0 /10 ×5

流式投递 10.0 /10 ×5 10.0 /10 ×5 0.0 /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 94 v3.24.0 98 v3.24.0

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 流式投递 buffer_dump_match
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 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 5315 ms 10616 ms 9428 ms 6537 ms

输出速度 67.6 tok/s 75.9 tok/s 143.2 tok/s 70.1 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 ⓘ

$0.2005

$0.2053

$0.2192

$0.2006

缓存读取占比 ⓘ 70% 70% 69% 70%

揭晓

通道

官方基准

服务商 Aiide ↗

通道O-Max

服务商 TopRouterCN ↗

通道O-Max

服务商 LingxiCode ↗

通道M-

返回列表