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。

4 通道 · 5 步骤

2026/06/16 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

AIMZ / M-Max
```
评测失败
```

步骤 / 指标

ClaudeCN

O-Max

PackyCode

cc-Zeus

官方基准

luminai

M-Kiro/Antigravity

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 15:04:58 ~ 15:05:08 (5.2s) 15:05:00 ~ 15:05:05 (4.1s) 15:05:02 ~ 15:05:12 (5.2s) 15:04:54 ~ 15:05:04 (8.4s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 3,715 ms 2,367 ms 3,461 ms 6,775 ms

首文本(SSE delta) 3,716 ms 2,402 ms 3,463 ms 6,806 ms

总耗时 3,969 ms 2,773 ms 4,048 ms 6,975 ms

输入 3 3 3 1,037

输出 5 5 5 1

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

2,225

5m: 2,225 / 1h: 0

缓存读取 0 0 0 25,590

响应

pong

pong

pong

pong

步骤 2: identity text

时间 15:08:21 ~ 15:08:32 (6.3s) 15:08:54 ~ 15:09:00 (3.6s) 15:07:35 ~ 15:07:46 (6.9s) 15:06:46 ~ 15:06:56 (7.8s)

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) 3,684 ms 1,888 ms 5,423 ms 4,594 ms

首文本(SSE delta) 3,685 ms 1,889 ms 5,424 ms 4,595 ms

总耗时 4,097 ms 2,360 ms 5,865 ms 5,003 ms

输入 3 3 3 168

输出 22 22 22 24

缓存创建

178

5m: 0 / 1h: 178

178

5m: 0 / 1h: 178

178

5m: 0 / 1h: 178

1,731

5m: 1,731 / 1h: 0

缓存读取 32,318 32,318 32,318 27,124

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 15:11:37 ~ 15:11:47 (6.4s) 15:11:15 ~ 15:11:20 (3.2s) 15:09:08 ~ 15:09:13 (3.7s) 15:10:06 ~ 15:10:46 (37.5s)

提示词

查看本步 Prompt

Knowledge cutoff date? Reply with YYYY-MM only.

HTTP 头(TTFB) 4,620 ms 1,870 ms 2,525 ms 4,720 ms

首文本(SSE delta) 4,621 ms 1,871 ms 2,638 ms 4,724 ms

总耗时 5,015 ms 2,103 ms 2,710 ms 4,728 ms

输入 3 3 3 25

输出 8 8 8 4

缓存创建

5m: 0 / 1h: 38

5m: 0 / 1h: 57

1,452

5m: 1,452 / 1h: 0

缓存读取 32,496 32,496 32,496 27,594

响应

2025-08

2025-08

2025-08

2025-08

步骤 4: identity_free text

时间 15:13:47 ~ 15:13:57 (5.8s) 15:15:06 ~ 15:15:16 (5.7s) 15:11:02 ~ 15:11:12 (5.2s) 15:13:11 ~ 15:13:21 (6.7s)

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) 3,757 ms 2,519 ms 3,549 ms 5,025 ms

首文本(SSE delta) 3,758 ms 2,520 ms 3,883 ms 5,259 ms

总耗时 4,624 ms 3,536 ms 4,196 ms 5,327 ms

输入 3 3 3 31

输出 39 55 41 24

缓存创建

5m: 0 / 1h: 39

5m: 0 / 1h: 35

5m: 0 / 1h: 39

1,453

5m: 1,453 / 1h: 0

缓存读取 32,534 32,534 32,553 27,624

输出速度 45.0 tok/s 54.1 tok/s 131.0 tok/s -

响应

我是 Claude，由 Anthropic 打造的 AI 助手。当前版本为 Claude Sonnet 4.6。

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

我是 Claude，由 Anthropic 公司打造的 AI 助手。当前版本为 claude-sonnet-4-6。

我是 Claude Sonnet 4.6，由 Anthropic 开发的 AI 助手。

步骤 5: knowledge_recall text

时间 15:17:27 ~ 15:17:37 (6.6s) 15:17:57 ~ 15:18:07 (6.7s) 15:14:24 ~ 15:14:34 (5.6s) 15:15:17 ~ 15:15:27 (8.9s)

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) 2,824 ms 2,105 ms 2,756 ms 4,302 ms

首文本(SSE delta) 3,282 ms 2,106 ms 2,758 ms 7,161 ms

总耗时 5,393 ms 4,567 ms 4,572 ms 7,788 ms

输入 3 3 3 800

输出 198 205 198 211

缓存创建

8,001

5m: 0 / 1h: 8,001

8,013

5m: 0 / 1h: 8,013

8,022

5m: 0 / 1h: 8,022

331

5m: 331 / 1h: 0

缓存读取 0 0 0 6,306

输出速度 93.8 tok/s 83.3 tok/s 109.2 tok/s burst

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

总计

总输入(含缓存) 137,937 137,945 137,996 123,491

总输出 272 295 274 264

总缓存创建

40,574

5m: 0 / 1h: 40,574

40,582

5m: 0 / 1h: 40,582

40,614

5m: 0 / 1h: 40,614

7,192

5m: 7,192 / 1h: 0

总缓存读取 97,348 97,348 97,367 114,238

输出速度 79.6 tok/s 74.8 tok/s 112.4 tok/s burst

总执行时间 30.3s 23.2s 26.6s 1m 9.2s

总墙钟时间

12m 38.8s

含步骤间等待

13m 6.8s

含步骤间等待

9m 31.8s

含步骤间等待

10m 32.8s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.1855

Anthropic: Claude Sonnet 4.6

$0.1859

Anthropic: Claude Sonnet 4.6

$0.1857

Anthropic: Claude Sonnet 4.6

$0.0613

Anthropic: Claude Sonnet 4.6

通道指纹

来源步骤 knowledge_recall knowledge_recall knowledge_recall knowledge_recall

平台 one-api (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 - cloudflare

ID 格式 msg_013UUnH7mLd3nWWxU8RAh5Av msg_01DSZW27AimxhJkQP1euFtQn msg_013KnoHpWr2r88REHdRipW2N msg_01UEHbNPgoJuZPrPXrHKBadVVn

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	cf-ray: a0c808f6e8b166b8-AMS server: cloudflare x-oneapi-request-id: 20260616151729734314166GpIt5SR6	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	a0c808f6e8b166b8-AMS
cc-Zeus	via: 1.1 Caddy cf-ray: a0c809b8baa2e9e0-LAX server: cloudflare x-oneapi-request-id: 202606161518005698828225ee3qokO	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-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	a0c809b8baa2e9e0-LAX
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_011Cc6XTasAH744bZMdKmXsd
M-Kiro/Antigravity	cf-ray: a0c805ca9a14b1bd-AMS server: cloudflare x-oneapi-request-id: 202606160715191455815388268d9d6nY0mvjz7	id_format: msg_prefix extra_fields: ["container"] has_service_tier: true has_inference_geo: false 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.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a0c805ca9a14b1bd-AMS

协议指纹评分（机器自动）

总分 / 100 92 94 95 82

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 7.3 /10 ×20 7.3 /10 ×20 7.3 /10 ×20 10.0 /10 ×20

缓存 TTL 一致 10.0 /10 ×15 10.0 /10 ×15 10.0 /10 ×15 4.0 /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 0.0 /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 0.0 /10 ×5

延迟基线 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 9.1 /10 ×5

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

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

SDK 一致 10.0 /10 ×2 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 92 v3.17.0 94 v3.17.0 基准（参考） 82 v3.17.0

雷达图例

共 18 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 自由身份 identity_free_clean
5 停止原因 stop_reason_present
6 系统提示纯净 system_prompt_clean
7 Service Tier service_tier_present
8 缓存命中比 cache_hit_ratio_match
9 缓存 TTL 一致 cache_ttl_consistency
10 推理地区 inference_geo_present
11 缓存连续 cache_continuity_intra
12 知识召回 knowledge_recall_match
13 延迟基线 latency_baseline_match
14 原生 msg-ID anthropic_msg_id_format
15 Sliding 缓存 cache_sliding_correctness
16 结构化身份 identity_structured_match
17 中文遵循 instruction_following_lang
18 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 4620 ms 3068 ms 4278 ms 5964 ms

输出速度 79.6 tok/s 74.8 tok/s 112.4 tok/s burst

完成步骤 5/5 成功 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 ⓘ

$0.1855

$0.1859

$0.1857

$0.0613

缓存读取占比 ⓘ 71% 71% 71% 93%

揭晓

通道

服务商 ClaudeCN ↗

通道O-Max

服务商 PackyCode ↗

通道cc-Zeus

官方基准

服务商 luminai ↗

通道M-Kiro/Antigravity

返回列表