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

2026/06/18 运行日期

claude-opus-4-8 官方基准

2 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

DBAI / M-
```
评测失败
```

步骤 / 指标

SSSAiCode

O-Max

ByteCatCode

O-Max

PackyCode

cc-Zeus

官方基准

基本信息

服务名 Claude Code Claude Code Claude Code Claude Code

模型 claude-opus-4-8 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 claude-cli v2.1.160

偏差标红基于官方基准

步骤 1: ping text

时间 10:52:38 ~ 10:52:43 (3.7s) 10:52:34 ~ 10:52:39 (4.5s) 10:52:36 ~ 10:52:41 (3.2s) 10:52:42 ~ 10:52:47 (3.9s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,127 ms 2,984 ms 1,903 ms 2,703 ms

首文本(SSE delta) 2,237 ms - 1,905 ms 2,704 ms

总耗时 2,385 ms 3,233 ms 2,055 ms 2,933 ms

输入 1,428 2 1,454 1,454

输出 4 4 4 4

缓存创建

29,756

5m: 0 / 1h: 29,756

36,616

5m: 0 / 1h: 36,616

30,223

5m: 0 / 1h: 30,223

30,222

5m: 0 / 1h: 30,222

缓存读取 0 0 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 10:53:59 ~ 10:54:04 (3.9s) 10:55:17 ~ 10:55:27 (5.0s) 10:53:41 ~ 10:53:46 (3.5s) 10:56:23 ~ 10:56:28 (3.1s)

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。严格按以下 3 行格式输出，全部小写英文，不要任何其他文字、解释、标点：
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) 1,694 ms 3,239 ms 2,142 ms 1,716 ms

首文本(SSE delta) 2,105 ms - 2,143 ms 1,717 ms

总耗时 2,182 ms 3,612 ms 2,541 ms 2,093 ms

输入 2 2 2 2

输出 30 28 28 28

缓存创建

1,617

5m: 0 / 1h: 1,617

5m: 0 / 1h: 0

1,643

5m: 0 / 1h: 1,643

1,643

5m: 0 / 1h: 1,643

缓存读取 29,756 36,828 30,223 30,222

响应

vendor: anthropic
brand: claude
model: claude-opus-4-20250514

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

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 10:57:38 ~ 10:57:48 (7.1s) 10:57:45 ~ 10:57:50 (3.9s) 10:56:01 ~ 10:56:06 (3.2s) 11:00:24 ~ 11:00:34 (5.4s)

提示词

查看本步 Prompt

你掌握的世界知识截止于何时？YYYY-MM 格式作答，不解释。

HTTP 头(TTFB) 6,121 ms 2,503 ms 1,809 ms 3,929 ms

首文本(SSE delta) 6,242 ms - 1,810 ms 3,931 ms

总耗时 6,305 ms 2,736 ms 2,045 ms 4,297 ms

输入 2 2 2 2

输出 6 6 6 6

缓存创建

5m: 0 / 1h: 64

245

5m: 0 / 1h: 245

5m: 0 / 1h: 62

5m: 0 / 1h: 54

缓存读取 31,373 36,616 31,866 31,865

响应

2025-01

2026-01

2026-01

2026-01

步骤 4: identity_free text

时间 11:00:10 ~ 11:00:15 (3.7s) 11:00:52 ~ 11:01:02 (5.1s) 10:58:59 ~ 10:59:04 (4.1s) 11:02:05 ~ 11:02:10 (3.9s)

提示词

查看本步 Prompt

用中文回答：你是谁？由谁开发？50 字以内。

HTTP 头(TTFB) 1,900 ms 2,828 ms 2,125 ms 2,001 ms

首文本(SSE delta) 2,807 ms - 2,126 ms 2,002 ms

总耗时 2,930 ms 4,034 ms 3,082 ms 2,796 ms

输入 2 2 2 2

输出 54 59 60 54

缓存创建

5m: 0 / 1h: 31

5m: 0 / 1h: 39

5m: 0 / 1h: 37

缓存读取 31,437 36,861 31,928 31,919

输出速度 - 48.9 tok/s 62.8 tok/s 68.0 tok/s

响应

我是 Claude,一个由 Anthropic 开发的 AI 助手。我能帮助你完成写作、分析、编程、问答等各类任务。

我是 Claude,由 Anthropic 开发的 AI 助手,具体模型为 Claude Opus 4.8,可协助编程、写作、分析等任务。

我是 Claude，由 Anthropic 开发的人工智能助手，基于 Claude Opus 4.8 模型，可帮助处理软件工程及多种任务。

我是 Claude，由 Anthropic 开发的 AI 助手，属于 Claude 模型系列，当前为 Opus 4.8 版本。

步骤 5: knowledge_recall text

时间 11:03:03 ~ 11:03:09 (4.6s) 11:02:35 ~ 11:02:50 (11.1s) 11:01:59 ~ 11:02:09 (8.5s) 11:04:06 ~ 11:04:17 (8.3s)

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) 1,190 ms 4,413 ms 2,276 ms 2,316 ms

首文本(SSE delta) 3,699 ms - 5,098 ms 4,824 ms

总耗时 3,764 ms 9,963 ms 7,482 ms 7,316 ms

输入 2 2 2 2

输出 317 712 687 690

缓存创建

4,276

5m: 0 / 1h: 4,276

50,447

5m: 0 / 1h: 50,447

4,781

5m: 0 / 1h: 4,781

4,764

5m: 0 / 1h: 4,764

缓存读取 0 0 0 0

输出速度 burst 128.3 tok/s burst 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

步骤 6: digit_count text

时间 11:04:32 ~ 11:04:37 (1.3s) 11:04:29 ~ 11:04:34 (3.5s) 11:03:48 ~ 11:03:53 (2.4s) 11:07:18 ~ 11:07:23 (3.3s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=703223645485108124328718781292066172510874332805500316637553558448049245

HTTP 头(TTFB) - 1,965 ms 1,116 ms 1,462 ms

首文本(SSE delta) - - 1,117 ms 1,466 ms

总耗时 - 2,370 ms 1,496 ms 2,298 ms

输入 - 211 212 211

输出 - 19 19 19

缓存创建

5m: 0 / 1h: 0

缓存读取 - 0 0 0

响应

失败

评测失败

{"n":72,"c":[7,5,5]}

{"n":70,"c":[6,5,2]}

{"n":70,"c":[8,5,4]}

总计

总输入(含缓存)

129,746

仅前 6 步

197,865

132,439

132,399

总输出

411

仅前 6 步

828

804

801

总缓存创建

35,744

5m: 0 / 1h: 35,744

仅前 6 步

87,339

5m: 0 / 1h: 87,339

36,748

5m: 0 / 1h: 36,748

36,720

5m: 0 / 1h: 36,720

总缓存读取

92,566

仅前 6 步

110,305

94,017

94,006

输出速度

burst

仅前 6 步

114.1 tok/s

62.8 tok/s

68.0 tok/s

总执行时间

24.3s

仅前 6 步

33.0s

25.0s

27.8s

总墙钟时间

11m 59.0s

含步骤间等待

仅前 6 步

12m 0.0s

含步骤间等待

11m 17.0s

含步骤间等待

14m 40.9s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.2871

Anthropic: Claude Opus 4.8 (部分)

$0.6228

Anthropic: Claude Opus 4.8

$0.3052

Anthropic: Claude Opus 4.8

$0.3049

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 knowledge_recall 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_012U8HxTFAqJ5GWYmFZmAN4g msg_01F8wQfxzzKTH8cqUZNQd7ks msg_01CNMUgSKvxXWgsPAdcM4xFL msg_01JadM2mqngEt5Kg3bFdETE2

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: a0d70f107b324818-LAX server: Photon-Edge set-cookie: _cfuvid=J9x5Qx.mfL_bIdpTGYlXLLEzO_ncifs3odzN8mdUeak-1781751785.0408578-1.0.1.1-ib9dwwmXFrTQN9PobWau6g64bas8Bl5cpyY0V2zpApc; 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	1781751784984-strqzg2ack7ci req_011Cc9yujkiA2kBed3GhMi2z a0d70f107b324818-LAX
O-Max	server: nginx/1.29.8 x-oneapi-request-id: 202606180304303791203178268d9d61R4qzQx9	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-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
cc-Zeus	via: 1.1 Caddy cf-ray: a0d710245a4ae9e5-LAX server: cloudflare x-oneapi-request-id: 20260618110349207482844xjPwvFfW	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	a0d710245a4ae9e5-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_011Cc9zEUjrUihryhFkcGGtE

协议指纹评分（机器自动）

总分 / 100 92 98 100

基线状态已对照基线已对照基线已对照基线

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

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

缓存命中比 — 9.5 /10 ×20 10.0 /10 ×20 10.0 /10 ×20

身份(结构) — 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

身份(自由) — 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7

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

Req-ID 透传 — 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

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

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

系统提示纯净 — 0.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8

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

流式投递 — 未计入 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 92 v3.22.0 98 v3.22.0 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 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 中文遵循 instruction_following_lang
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 3513 ms 4325 ms 3117 ms 3622 ms

输出速度 burst 114.1 tok/s 62.8 tok/s 68.0 tok/s

完成步骤 5/6 成功 · 1 失败 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 ⓘ

$0.2871 (部分)

$0.6228

$0.3052

$0.3049

缓存读取占比 ⓘ 71% (部分) 56% 71% 71%

揭晓

通道

服务商 SSSAiCode ↗

通道O-Max

服务商 ByteCatCode ↗

通道O-Max

服务商 PackyCode ↗

通道cc-Zeus

官方基准

返回列表