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。

3 通道 · 6 步骤

2026/07/01 运行日期

claude-sonnet-4-6 官方基准

2 任务失败执行不完整

已揭晓揭晓进度

⚠ 2 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
```
FastCode / cc
```
评测失败
```

步骤 / 指标

SAIAi

O-Max

sucui

O-Max

官方基准

基本信息

服务名 Claude Code Claude Code Claude Code

模型 claude-sonnet-4-6 claude-sonnet-4-6 claude-sonnet-4-6

客户端 claude-cli v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195

偏差标红基于官方基准

步骤 1: ping text

时间 22:43:57 ~ 22:44:02 (3.6s) 22:43:59 ~ 22:44:04 (4.1s) 22:44:03 ~ 22:44:08 (3.2s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,314 ms 2,507 ms 2,171 ms

首文本(SSE delta) 2,316 ms 2,508 ms 2,173 ms

总耗时 2,462 ms 2,891 ms 2,321 ms

输入 3 3 3

输出 5 5 5

缓存创建

5,991

5m: 0 / 1h: 5,991

5,991

5m: 0 / 1h: 5,991

5m: 0 / 1h: 0

缓存读取 14,884 14,884 20,875

响应

pong

pong

pong

步骤 2: identity text

时间 22:46:04 ~ 22:46:09 (4.4s) 22:47:12 ~ 22:47:17 (3.4s) 22:47:40 ~ 22:47:45 (4.3s)

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) 2,906 ms 1,969 ms 2,221 ms

首文本(SSE delta) 2,908 ms 1,970 ms 2,223 ms

总耗时 3,397 ms 2,341 ms 3,196 ms

输入 3 3 3

输出 22 22 22

缓存创建

202

5m: 0 / 1h: 202

202

5m: 0 / 1h: 202

5m: 0 / 1h: 0

缓存读取 20,875 20,875 21,077

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

步骤 3: cutoff text

时间 22:49:47 ~ 22:49:57 (5.5s) 22:49:16 ~ 22:49:21 (3.8s) 22:50:53 ~ 22:50:58 (3.4s)

提示词

查看本步 Prompt

Knowledge cutoff date? Reply with YYYY-MM only.

HTTP 头(TTFB) 4,224 ms 2,789 ms 2,077 ms

首文本(SSE delta) 4,357 ms 2,790 ms 2,253 ms

总耗时 4,489 ms 2,790 ms 2,330 ms

输入 3 3 3

输出 8 8 8

缓存创建

5m: 0 / 1h: 38

5m: 0 / 1h: 55

缓存读取 21,077 21,077 21,077

响应

2025-08

2025-08

2025-08

步骤 4: identity_free text

时间 22:51:46 ~ 22:51:56 (5.3s) 22:51:55 ~ 22:52:00 (4.0s) 22:54:43 ~ 22:54:53 (6.3s)

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) 3,407 ms 1,897 ms 4,235 ms

首文本(SSE delta) 3,798 ms 1,897 ms 4,236 ms

总耗时 4,348 ms 2,694 ms 5,243 ms

输入 3 3 3

输出 46 48 44

缓存创建

5m: 0 / 1h: 39

5m: 0 / 1h: 43

5m: 0 / 1h: 39

缓存读取 21,115 21,132 21,132

输出速度 83.6 tok/s 60.2 tok/s 43.7 tok/s

响应

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。我能帮助完成写作、编程、分析、问答等多种任务。

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。

步骤 5: knowledge_recall text

时间 22:54:51 ~ 22:55:06 (11.5s) 22:54:39 ~ 22:54:49 (9.1s) 22:58:30 ~ 22:58:50 (7.2s)

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) 1,713 ms 4,682 ms 1,714 ms

首文本(SSE delta) 2,118 ms 4,716 ms 1,715 ms

总耗时 10,316 ms 7,263 ms 3,564 ms

输入 3 3 3

输出 690 204 205

缓存创建

6,657

5m: 0 / 1h: 6,657

6,680

5m: 0 / 1h: 6,680

6,672

5m: 0 / 1h: 6,672

缓存读取 2,131 2,131 2,131

输出速度 84.2 tok/s 80.1 tok/s 110.9 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

步骤 6: digit_count text

时间 22:57:10 ~ 22:57:30 (16.9s) 22:58:28 ~ 22:58:53 (22.7s) 23:02:16 ~ 23:02:36 (17.5s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=997469747255998365651351610495427457013082318121169693118257777164311352

HTTP 头(TTFB) 835 ms 2,235 ms 1,417 ms

首文本(SSE delta) 837 ms 2,237 ms 1,816 ms

总耗时 15,283 ms 19,045 ms 15,037 ms

输入 164 164 164

输出 1,271 1,467 1,148

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0

输出速度 88.0 tok/s 87.3 tok/s 86.8 tok/s

响应

**Counting the string:**

`997469747255998365651351610495427457013082318121169693118257777164311352`

**Length:** Splitting into groups of 10:
`9974697472` `5599836565` `1351610495` `4274570130` `8231

## Counting digits in s

**s** = `997469747255998365651351610495427457013082318121169693118257777164311352`

### Step 1 — Length

Splitting into groups of 10:
```
9974697472  55998365651  → wait, let

## Counting digits in s

**s** = `997469747255998365651351610495427457013082318121169693118257777164311352`

### Length
Splitting into groups of 10:
```
9974697472 | 5599836565 | 1351610495 | 42745701

总计

总输入(含缓存) 93,188 93,249 93,237

总输出 2,042 1,754 1,432

总缓存创建

12,927

5m: 0 / 1h: 12,927

12,971

5m: 0 / 1h: 12,971

6,766

5m: 0 / 1h: 6,766

总缓存读取 80,082 80,099 86,292

输出速度 86.5 tok/s 85.3 tok/s 86.9 tok/s

总执行时间 47.1s 47.0s 41.8s

总墙钟时间

13m 33.0s

含步骤间等待

14m 54.1s

含步骤间等待

18m 33.5s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.1037

Anthropic: Claude Sonnet 4.6

$0.0995

Anthropic: Claude Sonnet 4.6

$0.0733

Anthropic: Claude Sonnet 4.6

通道指纹

来源步骤 digit_count digit_count digit_count

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

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

CDN - cloudflare -

ID 格式 msg_017sCgLeAqoUSvez4XUJgXD1 msg_017qKhsa1h1T6G1wvncbaxpN msg_01NVbKTJDUGGFR87Pbts3baG

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

O-Max

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_011CcbXt4rS6qG1QXshRddCR

O-Max

via: 1.1 Caddy
cf-ray: a14644f6cc4a5499-FRA
server: cloudflare
x-new-api-version: v0.12.10
x-oneapi-request-id: 202607011458322129732638268d9d6XARRU8Vd

id_format: msg_prefix
via_chain: ["1.1 Caddy"]
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-rayhdr:viabody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body

a14644f6cc4a5499-FRA

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_011CcbYGjSWmHFKNi5TfbVS5

协议指纹评分（机器自动）

总分 / 100 97 98 100

基线状态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

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

延迟基线 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

缓存连续性 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

原生 msg-ID 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

身份(结构) 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

service_tier 10.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6

知识截止 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

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

流式投递 0.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

stop_reason 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3

Req-ID 透传 10.0 /10 ×2 0.0 /10 ×2 10.0 /10 ×2

SDK 一致 10.0 /10 ×2 10.0 /10 ×2 10.0 /10 ×2

综合结论

与基线相似度 97 v3.26.0 98 v3.26.0 基准（参考）

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 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 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 6716 ms 6171 ms 5282 ms

输出速度 86.5 tok/s 85.3 tok/s 86.9 tok/s

完成步骤 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 ⓘ

$0.1037

$0.0995

$0.0733

缓存读取占比 ⓘ 86% 86% 93%

揭晓

通道

服务商 SAIAi ↗

通道O-Max

服务商 sucui ↗

通道O-Max

官方基准

返回列表