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

2026/06/22 运行日期

claude-sonnet-4-6 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

官方基准

duckcoding

cc专用

SudoCode

M-Max

AIMZ

M-Max

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 21:31:43 ~ 21:31:53 (5.3s) 21:31:35 ~ 21:31:40 (3.9s) 21:31:39 ~ 21:31:49 (5.4s) 21:31:41 ~ 21:31:51 (6.2s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 3,907 ms 2,657 ms 3,407 ms 3,616 ms

首文本(SSE delta) 3,909 ms 2,659 ms 3,410 ms 3,748 ms

总耗时 4,071 ms 2,766 ms 4,009 ms 3,791 ms

输入 3 3 3 3

输出 5 5 5 5

缓存创建

32,318

5m: 0 / 1h: 32,318

32,318

5m: 0 / 1h: 32,318

32,318

5m: 0 / 1h: 32,318

31,985

5m: 0 / 1h: 31,985

缓存读取 0 0 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 21:34:49 ~ 21:34:54 (3.4s) 21:32:42 ~ 21:32:47 (4.9s) 21:34:18 ~ 21:34:23 (4.5s) 21:35:05 ~ 21:35:10 (4.4s)

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) 1,983 ms 3,315 ms 2,815 ms 2,919 ms

首文本(SSE delta) 1,984 ms 3,455 ms 2,817 ms 3,125 ms

总耗时 2,308 ms 3,900 ms 3,349 ms 3,215 ms

输入 3 3 3 3

输出 22 22 22 22

缓存创建

189

5m: 0 / 1h: 189

189

5m: 0 / 1h: 189

189

5m: 0 / 1h: 189

189

5m: 0 / 1h: 189

缓存读取 32,318 32,318 32,318 31,985

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-4-5

步骤 3: cutoff text

时间 21:37:40 ~ 21:37:45 (3.6s) 21:35:37 ~ 21:35:42 (3.6s) 21:36:16 ~ 21:36:26 (7.0s) 21:38:55 ~ 21:39:00 (3.9s)

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) 2,395 ms 2,555 ms 5,319 ms 2,434 ms

首文本(SSE delta) 2,400 ms 2,556 ms 5,320 ms 2,568 ms

总耗时 2,598 ms 2,883 ms 5,775 ms 2,756 ms

输入 3 3 3 3

输出 8 8 8 8

缓存创建

5m: 0 / 1h: 55

5m: 0 / 1h: 57

缓存读取 32,507 32,507 32,507 32,174

响应

2025-08

2025-08

2025-08

2025-04

步骤 4: identity_free text

时间 21:41:17 ~ 21:41:23 (3.9s) 21:37:26 ~ 21:37:31 (4.5s) 21:38:16 ~ 21:38:27 (6.4s) 21:42:49 ~ 21:42:59 (7.4s)

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) 2,071 ms 2,901 ms 3,601 ms 4,958 ms

首文本(SSE delta) 2,072 ms 2,935 ms 3,602 ms 6,252 ms

总耗时 2,934 ms 3,764 ms 5,332 ms 6,253 ms

输入 3 3 3 3

输出 55 46 55 45

缓存创建

5m: 0 / 1h: 39

5m: 0 / 1h: 35

5m: 0 / 1h: 41

缓存读取 32,562 32,562 32,562 32,231

输出速度 63.8 tok/s 55.5 tok/s 31.8 tok/s burst

响应

我是 Claude，由 Anthropic 打造的 AI 助手。当前版本为 Claude Sonnet 4.6，专为对话、代码、分析等任务设计。

我是 Claude，由 Anthropic 公司打造的 AI 助手，当前运行的模型版本为 claude-sonnet-4-6。

我是 Claude，由 Anthropic 开发的 AI 助手。我基于大型语言模型构建，旨在提供安全、有益的对话与任务协助。

我叫 Claude，是由 Anthropic 开发的 AI 助手。目前运行的是 Claude Sonnet 4.5 模型。

步骤 5: knowledge_recall text

时间 21:42:54 ~ 21:43:04 (6.2s) 21:38:59 ~ 21:39:09 (6.2s) 21:39:58 ~ 21:40:08 (9.3s) 21:45:47 ~ 21:45:57 (5.7s)

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) 2,662 ms 2,162 ms 5,639 ms 2,047 ms

首文本(SSE delta) 2,664 ms 3,157 ms 5,651 ms 4,528 ms

总耗时 4,956 ms 4,738 ms 8,280 ms 4,689 ms

输入 3 3 3 3

输出 205 205 204 198

缓存创建

8,045

5m: 0 / 1h: 8,045

8,036

5m: 0 / 1h: 8,036

8,041

5m: 0 / 1h: 8,041

7,706

5m: 0 / 1h: 7,706

缓存读取 0 0 0 0

输出速度 89.4 tok/s 129.7 tok/s 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 21:44:46 ~ 21:45:06 (16.9s) 21:42:22 ~ 21:42:37 (12.0s) 21:42:29 ~ 21:42:49 (18.5s) 21:48:33 ~ 21:48:58 (21.5s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=678816412472359121621672187284165274195702283439550209912855087899606721

HTTP 头(TTFB) 1,901 ms 2,179 ms 2,200 ms 1,859 ms

首文本(SSE delta) 1,903 ms 2,203 ms 2,225 ms 2,526 ms

总耗时 15,925 ms 11,274 ms 17,355 ms 19,351 ms

输入 164 164 164 110

输出 1,225 721 1,197 1,231

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0

输出速度 87.4 tok/s 79.5 tok/s 79.1 tok/s 73.2 tok/s

响应

```json
{"n":72,"c":[5,8,7]}
```

**Verification walkthrough:**

| # | digit | # | digit | # | digit | # | digit |
|---|---|---|---|---|---|---|---|
|1|6|19|6|37|1|55|9|
|2|**7**|20|2|38|**9**|56|1|
|

```json
{"n":72,"c":[5,8,7]}
```

## Counting digits in `s`

**s** = `678816412472359121621672187284165274195702283439550209912855087899606721`

### Step 1 – Total length

Splitting into groups of 10:

| Chunk | Chars |
|---|---|
| `6

```json
{"n":72,"c":[5,8,7]}
```

总计

总输入(含缓存) 138,212 138,203 138,204 136,493

总输出 1,520 1,007 1,491 1,509

总缓存创建

40,646

5m: 0 / 1h: 40,646

40,637

5m: 0 / 1h: 40,637

40,638

5m: 0 / 1h: 40,638

39,978

5m: 0 / 1h: 39,978

总缓存读取 97,387 97,387 97,387 96,390

输出速度 86.5 tok/s 84.7 tok/s 74.7 tok/s 73.2 tok/s

总执行时间 39.3s 35.1s 51.0s 49.1s

总墙钟时间

13m 23.1s

含步骤间等待

11m 2.1s

含步骤间等待

11m 10.0s

含步骤间等待

17m 17.2s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.2050

Anthropic: Claude Sonnet 4.6

$0.1972

Anthropic: Claude Sonnet 4.6

$0.2045

Anthropic: Claude Sonnet 4.6

$0.2018

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%) 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_01T4C8CMZpD5zv7dj5idhGpG msg_01KBpZngs7ccJcDzzrimjQHz msg_01TcQQck1ZbV6CiCP2QCQtdC msg_01NvxeThbXtMpQXujgBmM2C2

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_011CcJQ5cfvBEBeUDrxpBz6B
cc专用	server: Nginx x-oneapi-request-id: 202606221342235424628518268d9d6KzKte8JB	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	—
M-Max	server: nginx x-new-api-version: v1.0.0-rc.11 x-oneapi-request-id: 20260622214230561194077cXkqah83	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-Max	cf-ray: a0fbb6238e12c96e-AMS server: cloudflare x-new-api-version: v0.0.0 x-oneapi-request-id: 202606221348358178695048268d9d6krhcZVYp	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	a0fbb6238e12c96e-AMS

协议指纹评分（机器自动）

总分 / 100 98 96 95 83

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 8.3 /10 ×20 8.3 /10 ×20 8.3 /10 ×20 8.4 /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 5.0 /10 ×8

身份(结构) 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 6.7 /10 ×7

知识截止 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 5.0 /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 0.0 /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） 96 v3.24.0 95 v3.24.0 83 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 5465 ms 4888 ms 7350 ms 6676 ms

输出速度 86.5 tok/s 84.7 tok/s 74.7 tok/s 73.2 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 ⓘ

$0.2050

$0.1972

$0.2045

$0.2018

缓存读取占比 ⓘ 70% 70% 70% 71%

揭晓

通道

官方基准

服务商 duckcoding ↗

通道cc专用

服务商 SudoCode ↗

通道M-Max

服务商 AIMZ ↗

通道M-Max

返回列表