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

2026/06/28 运行日期

claude-opus-4-8 官方基准

1 通道分数 < 70 另含 3 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

DBAI / M-
```
评测失败
```
YunWu / O-Api
```
评测失败
```

步骤 / 指标

SSSAiCode

O-Max

FastCode

官方基准

基本信息

服务名 Claude Code Claude Code Claude Code

模型 claude-opus-4-8 claude-opus-4-8 claude-opus-4-8

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 19:03:33 ~ 19:03:43 (6.8s) 19:03:37 ~ 19:03:47 (7.8s) 19:03:41 ~ 19:03:46 (3.6s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 1,838 ms 5,182 ms 2,601 ms

首文本(SSE delta) 1,942 ms 5,183 ms 2,603 ms

总耗时 1,978 ms 5,657 ms 2,649 ms

输入 1,428 1,454 1,454

输出 4 4 4

缓存创建

29,758

5m: 0 / 1h: 29,758

30,222

5m: 0 / 1h: 30,222

30,222

5m: 0 / 1h: 30,222

缓存读取 0 0 0

响应

pong

pong

pong

步骤 2: identity text

时间 19:06:53 ~ 19:06:58 (3.2s) 19:05:11 ~ 19:05:21 (6.3s) 19:05:03 ~ 19:05:13 (5.1s)

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) 1,820 ms 3,645 ms 2,357 ms

首文本(SSE delta) 2,314 ms 3,646 ms 2,359 ms

总耗时 2,467 ms 4,929 ms 4,168 ms

输入 2 2 2

输出 32 28 28

缓存创建

1,617

5m: 0 / 1h: 1,617

1,643

5m: 0 / 1h: 1,643

1,643

5m: 0 / 1h: 1,643

缓存读取 29,758 30,222 30,222

响应

vendor: anthropic
brand: claude
model: claude-opus-4-1-20250805

vendor: anthropic
brand: claude
model: claude-opus-4-8

vendor: anthropic
brand: claude
model: claude-opus-4-8

步骤 3: cutoff text

时间 19:09:58 ~ 19:10:03 (2.4s) 19:06:41 ~ 19:06:51 (5.6s) 19:08:05 ~ 19:08:10 (3.5s)

提示词

查看本步 Prompt

请直接回答你的知识截止日期，格式 YYYY-MM，不要附加任何说明。

HTTP 头(TTFB) 1,424 ms 3,281 ms 2,225 ms

首文本(SSE delta) 1,545 ms 3,282 ms 2,227 ms

总耗时 1,630 ms 3,282 ms 2,511 ms

输入 2 2 2

输出 6 6 6

缓存创建

5m: 0 / 1h: 68

31,929

5m: 0 / 1h: 31,929

5m: 0 / 1h: 64

缓存读取 31,375 0 31,865

响应

2025-01

2026-01

2026-01

步骤 4: identity_free text

时间 19:12:59 ~ 19:13:04 (3.7s) 19:08:22 ~ 19:08:27 (4.6s) 19:09:54 ~ 19:09:59 (4.2s)

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) 2,125 ms 3,028 ms 2,134 ms

首文本(SSE delta) 2,644 ms 3,029 ms 2,136 ms

总耗时 2,775 ms 3,512 ms 3,085 ms

输入 2 2 2

输出 39 67 67

缓存创建

5m: 0 / 1h: 37

5m: 0 / 1h: 31

5m: 0 / 1h: 39

缓存读取 31,443 31,929 31,929

输出速度 - 138.7 tok/s 70.6 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手，属于 Claude 系列产品。

我是 Claude，由 Anthropic 开发的人工智能助手，基于 Claude Opus 4.8 模型。我可以帮助你完成编程、写作、分析等各类任务。

我是 Claude，由 Anthropic 开发的 AI 助手。我可以协助编程、写作、分析问题和日常对话，致力于提供有用、诚实且安全的帮助。

步骤 5: knowledge_recall text

时间 19:14:10 ~ 19:14:20 (5.5s) 19:09:43 ~ 19:09:58 (11.8s) 19:11:00 ~ 19:11:10 (6.4s)

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) 1,450 ms 2,987 ms 1,876 ms

首文本(SSE delta) 1,947 ms 7,004 ms 2,415 ms

总耗时 4,768 ms 8,942 ms 5,317 ms

输入 2 2 2

输出 348 755 355

缓存创建

4,273

5m: 0 / 1h: 4,273

4,781

5m: 0 / 1h: 4,781

4,789

5m: 0 / 1h: 4,789

缓存读取 0 0 0

输出速度 123.4 tok/s burst 122.3 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 19:18:13 ~ 19:18:18 (0.9s) 19:13:42 ~ 19:13:47 (3.9s) 19:13:04 ~ 19:13:09 (2.6s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=461769841323205261038930607588425280644339833558599488399571137625296251

HTTP 头(TTFB) - 1,855 ms 1,376 ms

首文本(SSE delta) - 1,856 ms 1,378 ms

总耗时 - 1,862 ms 1,665 ms

输入 - 211 211

输出 - 19 19

缓存创建

5m: 0 / 1h: 0

缓存读取 - 0 0

响应

失败

评测失败

{"n":72,"c":[5,4,9]}

{"n":72,"c":[5,5,9]}

总计

总输入(含缓存)

129,765

仅前 6 步

132,430

132,446

总输出

429

仅前 6 步

879

479

总缓存创建

35,753

5m: 0 / 1h: 35,753

仅前 6 步

68,606

5m: 0 / 1h: 68,606

36,757

5m: 0 / 1h: 36,757

总缓存读取

92,576

仅前 6 步

62,151

94,016

输出速度

123.4 tok/s

仅前 6 步

138.7 tok/s

109.6 tok/s

总执行时间

22.5s

仅前 6 步

40.0s

25.4s

总墙钟时间

14m 44.9s

含步骤间等待

仅前 6 步

10m 10.0s

含步骤间等待

9m 28.0s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.2876

Anthropic: Claude Opus 4.8 (部分)

$0.4902

Anthropic: Claude Opus 4.8

$0.2971

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 knowledge_recall digit_count digit_count

平台 direct (100%) direct (75%) direct (100%)

上游 Anthropic 直连 (100%) Anthropic 直连 (75%) Anthropic 直连 (100%)

CDN - - -

ID 格式 msg_013MKSNm6ovZaUkRURMASYvh msg_vrtx_01XHKQudc4UqH8RqrB3Wpstg msg_01SYFyeT7CjpbUcLdXiUypoF

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: a12c4437efea196e-LAX
server: Photon-Edge
set-cookie: _cfuvid=_1aC3.aWriorprQMq58tcAbAZKmbWLmMDbJ90uSHicY-1782645251.8225207-1.0.1.1-9sMUZ7FlquUm1BbRmzz2MC906uPCP3c577eLKvBpy9o; 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: 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

1782645251712-t7tzuaskfdgjr
req_011CcVZT28jJaaLRMyjVjy3x
a12c4437efea196e-LAX

server: nginx

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

body:id:msg_prefixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body

—

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_011CcVZN77yyeQtbdN7BQpnL

协议指纹评分（机器自动）

总分 / 100 73 98

基线状态已对照基线已对照基线

模型匹配 — 10.0 /10 ×14 10.0 /10 ×14

缓存连续性 — 10.0 /10 ×14 10.0 /10 ×14

sliding 5m — 7.7 /10 ×13 10.0 /10 ×13

缓存 TTL 一致 — 10.0 /10 ×15 10.0 /10 ×15

缓存命中比 — 0.0 /10 ×20 8.6 /10 ×20

身份(结构) — 10.0 /10 ×7 10.0 /10 ×7

知识截止 — 10.0 /10 ×7 10.0 /10 ×7

身份(自由) — 10.0 /10 ×7 10.0 /10 ×7

原生 msg-ID — 0.0 /10 ×8 10.0 /10 ×8

Req-ID 透传 — 0.0 /10 ×4 10.0 /10 ×4

stop_reason — 10.0 /10 ×3 10.0 /10 ×3

service_tier — 0.0 /10 ×6 10.0 /10 ×6

inference_geo — 0.0 /10 ×5 10.0 /10 ×5

SDK 一致 — 10.0 /10 ×2 10.0 /10 ×2

系统提示纯净 — 10.0 /10 ×8 10.0 /10 ×8

延迟基线 — 9.9 /10 ×5 10.0 /10 ×5

流式投递 — 10.0 /10 ×5 10.0 /10 ×5

综合结论

与基线相似度执行失败，不评分 73 v3.25.0 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 2724 ms 4697 ms 3233 ms

输出速度 123.4 tok/s 138.7 tok/s 109.6 tok/s

完成步骤 5/6 成功 · 1 失败 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 ⓘ

$0.2876 (部分)

$0.4902

$0.2971

缓存读取占比 ⓘ 71% (部分) 47% 71%

揭晓

通道

服务商 SSSAiCode ↗

通道O-Max

服务商 FastCode ↗

通道cc

官方基准

返回列表