模型对比 | RPDiag

测试说明点击展开 5 步 quick-probe-v1 详解

同一会话连续 5 步，覆盖 5 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。步与步之间随机延迟 1–4 分钟。第 3 步（cutoff）累计跨度 > 5 分钟保住 sliding cache 检测；全流程总跨度 > 6 分钟容纳新增的第 5 步。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 · 5 步骤

2026/06/16 运行日期

claude-haiku-4-5-20251001 官方基准

2 通道分数 < 70 另含 2 任务失败

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

Aiberm / cc
```
评测失败
```
0-0 / O-Max
```
评测失败
```

步骤 / 指标

官方基准

SSSAiCode

O-Max

HongMaCC

u-cc

基本信息

服务名 Claude Code Claude Code Claude Code

模型 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001

客户端 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 06:26:38 ~ 06:26:43 (3.7s) 06:26:32 ~ 06:26:47 (11.8s) 06:26:36 ~ 06:26:41 (3.7s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,198 ms 7,755 ms 2,200 ms

首文本(SSE delta) 2,199 ms 8,047 ms 2,201 ms

总耗时 2,569 ms 8,084 ms 2,201 ms

输入 10 10 0

输出 50 56 19

缓存创建

33,122

5m: 0 / 1h: 33,122

32,790

5m: 0 / 1h: 32,790

5m: 0 / 1h: 0

缓存读取 0 0 0

输出速度 135.1 tok/s burst -

响应

pong

pong

pong

步骤 2: identity text

时间 06:30:35 ~ 06:30:40 (4.4s) 06:29:00 ~ 06:29:15 (10.0s) 06:30:17 ~ 06:30:22 (4.0s)

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) 1,675 ms 1,623 ms 2,824 ms

首文本(SSE delta) 1,676 ms 9,056 ms 2,825 ms

总耗时 3,339 ms 9,278 ms 2,825 ms

输入 10 10 0

输出 194 729 214

缓存创建

241

5m: 0 / 1h: 241

247

5m: 0 / 1h: 247

5m: 0 / 1h: 0

缓存读取 33,122 32,790 0

输出速度 116.7 tok/s burst burst

响应

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

vendor: anthropic
brand: claude
model: claude-opus-4-6

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

步骤 3: cutoff text

时间 06:34:17 ~ 06:34:22 (3.5s) 06:33:00 ~ 06:33:05 (3.3s) 06:31:25 ~ 06:31:30 (3.2s)

提示词

查看本步 Prompt

请用 YYYY-MM 格式告诉我你的训练数据截止日期，无需多余文字。

HTTP 头(TTFB) 1,935 ms 1,684 ms 2,079 ms

首文本(SSE delta) 1,937 ms 2,374 ms 2,080 ms

总耗时 2,551 ms 2,409 ms 2,080 ms

输入 10 10 0

输出 81 84 42

缓存创建

237

5m: 0 / 1h: 237

769

5m: 0 / 1h: 769

5m: 0 / 1h: 0

缓存读取 33,363 33,037 0

输出速度 131.9 tok/s burst burst

响应

2025-02

2024-04

2025-02

步骤 4: identity_free text

时间 06:36:31 ~ 06:36:41 (8.0s) 06:35:58 ~ 06:36:03 (4.6s) 06:32:57 ~ 06:33:02 (3.7s)

提示词

查看本步 Prompt

中文回答：你叫什么、属于哪个产品、谁开发？50 字内。

HTTP 头(TTFB) 1,768 ms 1,024 ms 2,542 ms

首文本(SSE delta) 1,770 ms 3,830 ms 2,543 ms

总耗时 7,102 ms 3,870 ms 2,543 ms

输入 10 10 0

输出 757 504 70

缓存创建

121

5m: 0 / 1h: 121

124

5m: 0 / 1h: 124

5m: 0 / 1h: 0

缓存读取 33,600 33,806 0

输出速度 142.0 tok/s burst burst

响应

我叫Claude Haiku 4.5，由Anthropic公司开发，属于Claude产品。是一个轻量级AI助手，专注于快速高效的对话和编程任务。

我叫Claude，是Anthropic公司开发的AI助手。我属于Claude产品系列，目前是第四代模型。Anthropic是一家专注于AI安全研究的公司。

我是 Claude，Anthropic 开发的 AI 助手。

步骤 5: knowledge_recall text

时间 06:39:42 ~ 06:40:02 (18.5s) 06:38:08 ~ 06:38:28 (16.6s) 06:35:49 ~ 06:35:59 (6.5s)

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) 1,461 ms 1,062 ms 5,111 ms

首文本(SSE delta) 1,463 ms 15,250 ms 5,112 ms

总耗时 17,480 ms 15,749 ms 5,307 ms

输入 10 10 0

输出 2,707 2,398 1,233

缓存创建

9,096

5m: 0 / 1h: 9,096

9,052

5m: 0 / 1h: 9,052

5m: 0 / 1h: 0

缓存读取 0 0 0

输出速度 169.0 tok/s burst burst

响应

```json
{"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

```json
{"facts":{"super_bowl_lviii":"Kansas City Chiefs","oscars2024_best_picture":"Oppenheimer","ucl_2024":"UNKNOWN","nba_2024":"UNKNOWN","copa_america_2024":"UNKNOWN","euro2024":"UNKNOWN","nobel_pe

{"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

总计

总输入(含缓存) 142,952 142,665 0

总输出 3,789 3,771 1,578

总缓存创建

42,817

5m: 0 / 1h: 42,817

42,982

5m: 0 / 1h: 42,982

5m: 0 / 1h: 0

总缓存读取 100,085 99,633 0

输出速度 157.9 tok/s burst burst

总执行时间 38.2s 46.3s 21.1s

总墙钟时间

13m 24.8s

含步骤间等待

11m 56.8s

含步骤间等待

9m 23.8s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.0825

Anthropic: Claude Haiku 4.5

$0.0826

Anthropic: Claude Haiku 4.5

>=$0.0079

Anthropic: Claude Haiku 4.5 (成本不完整)

通道指纹

来源步骤 knowledge_recall knowledge_recall knowledge_recall

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

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

CDN - - -

ID 格式 msg_013XDevwCYWMHxaoivA1mEGY msg_01EdTdsfhH6ojPJecsgKyxt1 msg_52ea823819585155db3c0365

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: true
usage_has_cache_fields: true

body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body

req_011Cc5rDAQZdSy4teDVFXPQg

O-Max

cf-ray: a0c5103fec4c2f73-LAX
server: Photon-Edge
set-cookie: _cfuvid=8nkrkeZEKSc_r8CpT.GFerj08Q7EqSy6WtfE2Al8XRA-1781563089.9035378-1.0.1.1-_H_okpAlh3F7K5DhK7BASDvGTvZMWNDksMzsAaglNDQ; HttpOnly; SameSite=None; Secure; Path=/; Domain=api.anthropic.com

id_format: msg_prefix
extra_fields: ["stop_details"]
has_service_tier: true
has_inference_geo: true
model_has_date_suffix: true
usage_has_cache_fields: true

body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body

1781563089853-rz9g165420c4v
req_011Cc5r6Cz97xGGrRxBbJ98N
a0c5103fec4c2f73-LAX

u-cc

server: nginx
x-new-api-version: 1.0.10
x-oneapi-request-id: 202606152235511560341858268d9d68qvawqrK

id_format: msg_prefix
extra_fields: ["stop_details"]
has_service_tier: true
has_inference_geo: true
model_has_date_suffix: true
usage_has_cache_fields: true

hdr:x-new-api-versionhdr:x-oneapi-request-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body

—

协议指纹评分（机器自动）

总分 / 100 100 79 59

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 0.0 /10 ×20

缓存 TTL 一致 10.0 /10 ×15 10.0 /10 ×15 0.0 /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 5.0 /10 ×14

sliding 5m 10.0 /10 ×13 10.0 /10 ×13 5.0 /10 ×13

原生 msg-ID 10.0 /10 ×8 10.0 /10 ×8 0.0 /10 ×8

系统提示纯净 10.0 /10 ×8 5.0 /10 ×8 未计入

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

知识截止 10.0 /10 ×7 0.0 /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

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

延迟基线 10.0 /10 ×5 9.4 /10 ×5 10.0 /10 ×5

Req-ID 透传 10.0 /10 ×4 10.0 /10 ×4 0.0 /10 ×4

stop_reason 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

流式投递 — — —

综合结论

与基线相似度基准（参考） 79 v3.16.0 59 v3.16.0

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 Thinking 存在 thinking_present
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 Thinking 体量 thinking_volume_match
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 自报身份一致 self_identity_consistency
20 中文遵循 instruction_following_lang
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 6608 ms 7878 ms 2991 ms

输出速度 157.9 tok/s burst burst

完成步骤 5/5 成功 5/5 成功 5/5 成功

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.0825

$0.0826

>=$0.0079 (成本不完整)

缓存读取占比 ⓘ 70% 70% -

揭晓

通道

官方基准

服务商 SSSAiCode ↗

通道O-Max

服务商 HongMaCC ↗

通道u-cc

返回列表