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

2026/06/27 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

ClaudeZZ

R-kiro

SudoCode

M-Max

ClaudeCN

O-Max

官方基准

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 14:19:11 ~ 14:19:21 (7.8s) 14:19:09 ~ 14:19:14 (4.6s) 14:19:13 ~ 14:19:23 (5.7s) 14:19:15 ~ 14:19:25 (5.0s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 6,652 ms 3,323 ms 4,005 ms 3,886 ms

首文本(SSE delta) 6,654 ms 3,324 ms 4,006 ms 3,887 ms

总耗时 6,927 ms 3,543 ms 4,274 ms 3,952 ms

输入 3 3 3 3

输出 5 5 5 5

缓存创建

21,986

5m: 0 / 1h: 21,986

32,318

5m: 0 / 1h: 32,318

32,318

5m: 0 / 1h: 32,318

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 14:22:36 ~ 14:22:51 (10.3s) 14:20:15 ~ 14:20:20 (4.6s) 14:21:32 ~ 14:21:42 (5.2s) 14:21:15 ~ 14:21:25 (6.0s)

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。请只输出以下 3 行内容（label 小写，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) 8,912 ms 2,860 ms 3,134 ms 4,472 ms

首文本(SSE delta) 8,914 ms 2,862 ms 3,135 ms 4,474 ms

总耗时 9,548 ms 3,269 ms 3,665 ms 4,955 ms

输入 3 3 3 3

输出 22 22 22 22

缓存创建

185

5m: 0 / 1h: 185

178

5m: 0 / 1h: 178

178

5m: 0 / 1h: 178

178

5m: 0 / 1h: 178

缓存读取 21,986 32,318 32,318 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 14:26:27 ~ 14:26:37 (7.0s) 14:22:38 ~ 14:22:43 (4.0s) 14:23:03 ~ 14:23:13 (5.9s) 14:24:16 ~ 14:24:26 (5.0s)

提示词

查看本步 Prompt

Knowledge cutoff date? Reply with YYYY-MM only.

HTTP 头(TTFB) 5,705 ms 2,751 ms 4,077 ms 3,679 ms

首文本(SSE delta) 5,707 ms 2,752 ms 4,091 ms 4,033 ms

总耗时 5,932 ms 3,029 ms 4,928 ms 4,038 ms

输入 3 3 3 3

输出 8 8 8 8

缓存创建

5m: 0 / 1h: 62

5m: 0 / 1h: 55

5m: 0 / 1h: 38

5m: 0 / 1h: 57

缓存读取 22,171 32,496 32,496 32,496

响应

2025-08

2025-08

2025-08

2025-08

步骤 4: identity_free text

时间 14:30:13 ~ 14:30:23 (8.4s) 14:26:23 ~ 14:26:28 (4.3s) 14:24:27 ~ 14:24:37 (6.6s) 14:26:59 ~ 14:27:09 (5.9s)

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) 6,600 ms 2,929 ms 3,480 ms 4,085 ms

首文本(SSE delta) 6,603 ms 2,930 ms 3,481 ms 4,089 ms

总耗时 7,554 ms 3,323 ms 5,085 ms 4,870 ms

输入 3 3 3 3

输出 72 26 44 49

缓存创建

5m: 0 / 1h: 49

5m: 0 / 1h: 39

5m: 0 / 1h: 41

缓存读取 22,233 32,551 32,534 32,553

输出速度 75.7 tok/s - 27.4 tok/s 62.7 tok/s

响应

我是 Claude，由 Anthropic 公司打造的 AI 助手。目前运行的是 Claude Sonnet 4.6 模型，作为 Claude Code CLI 工具为您提供编程和软件工程方面的帮助。

我是 Claude，由 Anthropic 公司打造的 AI 助手。

我是 Claude，由 Anthropic 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，属于 Claude 产品系列。当前版本为 Claude Sonnet 4.6。

步骤 5: knowledge_recall text

时间 14:32:10 ~ 14:32:20 (6.5s) 14:27:47 ~ 14:27:57 (5.5s) 14:27:21 ~ 14:27:31 (9.3s) 14:29:03 ~ 14:29:13 (6.0s)

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) 3,497 ms 2,110 ms 5,819 ms 3,060 ms

首文本(SSE delta) 3,498 ms 2,111 ms 5,877 ms 3,062 ms

总耗时 5,680 ms 4,583 ms 8,138 ms 5,007 ms

输入 3 3 3 3

输出 205 204 205 204

缓存创建

6,119

5m: 0 / 1h: 6,119

8,005

5m: 0 / 1h: 8,005

8,006

5m: 0 / 1h: 8,006

8,032

5m: 0 / 1h: 8,032

缓存读取 2,136 0 0 0

输出速度 94.0 tok/s 82.5 tok/s 90.7 tok/s 104.9 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 14:34:54 ~ 14:35:09 (11.5s) 14:30:23 ~ 14:30:43 (19.3s) 14:28:45 ~ 14:29:05 (18.2s) 14:30:48 ~ 14:31:18 (25.1s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=113993764053041311797849806020893485817586338605762913480422561124414872

HTTP 头(TTFB) 3,323 ms 2,362 ms 2,589 ms 5,520 ms

首文本(SSE delta) 3,325 ms 2,385 ms 2,590 ms 5,527 ms

总耗时 10,605 ms 18,343 ms 16,991 ms 24,141 ms

输入 3 164 164 164

输出 875 1,318 1,250 2,046

缓存创建

3,823

5m: 0 / 1h: 3,823

5m: 0 / 1h: 0

缓存读取 2,136 0 0 0

输出速度 120.2 tok/s 82.6 tok/s 86.8 tok/s 109.9 tok/s

响应

Counting the string character by character:

**s** = `113993764053041311797849806020893485817586338605762913480422561124414872`

**Total length:** 72

**Zeros (0):** positions 10, 13, 26, 28, 30, 47,

## Counting digits in s

**s** = `113993764053041311797849806020893485817586338605762913480422561124414872`

### Length
Grouping into blocks of 10:
`1139937640` `5304131179` `7849806020` `8934858175`

```python
s = "113993764053041311797849806020893485817586338605762913480422561124414872"
n = len(s)          # 72
c0 = s.count('0')   # 7
c7 = s.count('7')   # 6
c9 = s.count('9')   # 6
```

**Verific

```
s = 113993764053041311797849806020893485817586338605762913480422561124414872
```

**Counting length:** Splitting into groups of 10:
`1139937640` `5304131179` `7849806020` `8934858175` `8633860576`

总计

总输入(含缓存) 102,904 138,139 138,106 138,172

总输出 1,187 1,583 1,534 2,334

总缓存创建

32,224

5m: 0 / 1h: 32,224

40,595

5m: 0 / 1h: 40,595

40,579

5m: 0 / 1h: 40,579

40,626

5m: 0 / 1h: 40,626

总缓存读取 70,662 97,365 97,348 97,367

输出速度 110.6 tok/s 82.6 tok/s 82.1 tok/s 107.7 tok/s

总执行时间 51.5s 42.3s 50.9s 52.9s

总墙钟时间

15m 58.0s

含步骤间等待

11m 33.8s

含步骤间等待

9m 52.0s

含步骤间等待

12m 3.0s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.1599

Anthropic: Claude Sonnet 4.6

$0.2057

Anthropic: Claude Sonnet 4.6

$0.2049

Anthropic: Claude Sonnet 4.6

$0.2171

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%) 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_016G4W2vZnh9BnYpMBGpBGzm msg_01CRMAgWh72zH8bR5K2rx5dH msg_01BRZ6KWibJ7qmeY352KWW5c msg_014cmPsfanTmFHSdYffaH4NL

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	via: 1.1 google cf-ray: 86f564680152c4d67c3e83c39670d180-IAD server: nginx	id_format: msg_prefix via_chain: ["1.1 google"] extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: false usage_has_cache_fields: true	hdr:viabody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_86f564680152c4d67c3e83c39670d180 86f564680152c4d67c3e83c39670d180-IAD
M-Max	server: nginx x-new-api-version: 0b8be5cf x-oneapi-request-id: 202606271430246928031249yKkMGhK	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-Max	cf-ray: a12264c2ba329fbd-AMS server: cloudflare x-oneapi-request-id: 20260627142847719226422Mkdz32Th	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	a12264c2ba329fbd-AMS
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_011CcTJ37yHk74hwYvt6ca9c

协议指纹评分（机器自动）

总分 / 100 92 97 98 100

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 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 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 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 8.9 /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 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

综合结论

与基线相似度 92 v3.25.0 97 v3.25.0 98 v3.25.0 基准（参考）

雷达图例

共 20 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 档位思考量 tier_thinking_volume_match
20 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 7708 ms 6015 ms 7180 ms 7827 ms

输出速度 110.6 tok/s 82.6 tok/s 82.1 tok/s 107.7 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 ⓘ

$0.1599

$0.2057

$0.2049

$0.2171

缓存读取占比 ⓘ 69% 70% 70% 70%

揭晓

通道

服务商 ClaudeZZ ↗

通道R-kiro

服务商 SudoCode ↗

通道M-Max

服务商 ClaudeCN ↗

通道O-Max

官方基准

返回列表