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

2026/06/17 运行日期

claude-opus-4-8 官方基准

1 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

DawAPI / cc
```
评测失败
```

步骤 / 指标

官方基准

ByteCatCode

O-Max

PackyCode

cc-Zeus

SAIAi

O-Max

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 20:52:28 ~ 20:52:38 (7.6s) 20:52:20 ~ 20:52:30 (6.2s) 20:52:26 ~ 20:52:36 (5.2s) 20:52:24 ~ 20:52:29 (3.7s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 6,291 ms 3,702 ms 2,855 ms 2,246 ms

首文本(SSE delta) 6,292 ms - 2,856 ms 2,247 ms

总耗时 6,475 ms 3,879 ms 3,152 ms 2,423 ms

输入 1,454 1,454 1,454 1,454

输出 4 4 4 4

缓存创建

30,222

5m: 0 / 1h: 30,222

30,222

5m: 0 / 1h: 30,222

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 20:55:35 ~ 20:55:45 (5.1s) 20:55:01 ~ 20:55:11 (5.1s) 20:56:10 ~ 20:56:15 (3.9s) 20:56:24 ~ 20:56:29 (3.6s)

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。自报身份，输出严格遵守以下 3 行格式（不允许 markdown、代码块、额外文本）：
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) 3,584 ms 2,985 ms 2,248 ms 2,288 ms

首文本(SSE delta) 3,585 ms - 2,250 ms 2,290 ms

总耗时 3,961 ms 3,699 ms 2,747 ms 2,677 ms

输入 2 2 2 2

输出 28 28 28 28

缓存创建

1,646

5m: 0 / 1h: 1,646

1,646

5m: 0 / 1h: 1,646

1,646

5m: 0 / 1h: 1,646

1,646

5m: 0 / 1h: 1,646

缓存读取 30,222 30,222 30,223 30,222

响应

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

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

步骤 3: cutoff text

时间 20:59:24 ~ 20:59:29 (4.3s) 20:57:54 ~ 20:57:59 (4.1s) 20:59:13 ~ 20:59:18 (4.1s) 20:58:51 ~ 20:58:56 (3.6s)

提示词

查看本步 Prompt

Knowledge cutoff date? Reply with YYYY-MM only.

HTTP 头(TTFB) 2,792 ms 2,540 ms 2,477 ms 2,370 ms

首文本(SSE delta) 2,793 ms - 2,815 ms 2,375 ms

总耗时 3,310 ms 2,801 ms 3,005 ms 2,614 ms

输入 2 2 2 2

输出 6 6 6 6

缓存创建

5m: 0 / 1h: 54

5m: 0 / 1h: 62

5m: 0 / 1h: 64

5m: 0 / 1h: 62

缓存读取 31,868 31,868 31,869 31,868

响应

2026-01

2025-01

2026-01

2026-01

步骤 4: identity_free text

时间 21:00:49 ~ 21:00:54 (4.5s) 21:01:56 ~ 21:02:06 (6.0s) 21:02:46 ~ 21:02:51 (4.1s) 21:01:52 ~ 21:02:02 (6.9s)

提示词

查看本步 Prompt

中文做个自我介绍：你是什么产品或助手？谁开发的？50 字内。

HTTP 头(TTFB) 2,188 ms 2,574 ms 2,715 ms 4,307 ms

首文本(SSE delta) 2,189 ms - 2,716 ms 4,354 ms

总耗时 3,462 ms 3,650 ms 3,143 ms 5,958 ms

输入 2 2 2 2

输出 84 61 67 66

缓存创建

5m: 0 / 1h: 39

缓存读取 31,922 31,930 31,933 31,930

输出速度 66.0 tok/s 56.7 tok/s - 41.1 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手。我能帮你写代码、分析问题、查找资料和完成各类软件工程任务。当前基于 Opus 4.8 模型，乐意为你提供帮助。

我是 Claude，由 Anthropic 开发的 AI 助手，基于 Claude Opus 4.8 模型，可协助编程、写作、分析等多种任务。

我是 Claude，由 Anthropic 开发的 AI 助手。我能协助编程、写作、分析和回答各类问题，致力于提供有帮助、诚实且安全的服务。

我是 Claude，由 Anthropic 开发的 AI 助手。我能帮你写代码、分析问题、查找资料和处理各类软件工程任务，擅长推理与协作。

步骤 5: knowledge_recall text

时间 21:04:03 ~ 21:04:18 (10.7s) 21:04:30 ~ 21:04:45 (11.2s) 21:06:39 ~ 21:06:54 (10.0s) 21:06:00 ~ 21:06:16 (13.6s)

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) 4,216 ms 3,129 ms 3,552 ms 7,233 ms

首文本(SSE delta) 6,678 ms - 6,392 ms 10,456 ms

总耗时 9,737 ms 9,988 ms 8,660 ms 12,605 ms

输入 2 2 2 2

输出 649 652 698 664

缓存创建

4,799

5m: 0 / 1h: 4,799

4,784

5m: 0 / 1h: 4,784

4,793

5m: 0 / 1h: 4,793

4,789

5m: 0 / 1h: 4,789

缓存读取 0 0 0 0

输出速度 burst 95.1 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 21:05:49 ~ 21:05:59 (7.7s) 21:05:55 ~ 21:06:30 (31.2s) 21:08:10 ~ 21:08:15 (3.2s) 21:08:49 ~ 21:08:54 (3.7s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=196308827564877376922467081675082031777612375957193289643333840984781687

HTTP 头(TTFB) 5,822 ms 11,860 ms 1,758 ms 2,334 ms

首文本(SSE delta) 5,823 ms - 1,759 ms 2,335 ms

总耗时 6,708 ms 29,671 ms 2,321 ms 2,717 ms

输入 211 2 212 211

输出 19 1,769 19 19

缓存创建

5m: 0 / 1h: 0

49,289

5m: 0 / 1h: 49,289

5m: 0 / 1h: 0

缓存读取 0 0 0 0

输出速度 - 99.3 tok/s - -

响应

{"n":70,"c":[6,11,3]}

{"n":72,"c":[5,13,6]}

{"n":70,"c":[6,11,5]}

{"n":70,"c":[7,9,6]}

总计

总输入(含缓存) 132,445 181,526 132,464 132,451

总输出 790 2,520 822 787

总缓存创建

36,760

5m: 0 / 1h: 36,760

86,042

5m: 0 / 1h: 86,042

36,765

5m: 0 / 1h: 36,765

36,758

5m: 0 / 1h: 36,758

总缓存读取 94,012 94,020 94,025 94,020

输出速度 66.0 tok/s 96.4 tok/s burst 41.1 tok/s

总执行时间 39.8s 1m 3.8s 30.6s 35.1s

总墙钟时间

13m 30.9s

含步骤间等待

14m 10.1s

含步骤间等待

15m 48.9s

含步骤间等待

16m 30.0s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.3049

Anthropic: Claude Opus 4.8

$0.6551

Anthropic: Claude Opus 4.8

$0.3057

Anthropic: Claude Opus 4.8

$0.3048

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count 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_018VY9SjrmTrYrYnbrqw3Hdy msg_01BdRoe85BttLFD7p7i4zXgh msg_01XPZvTyb6K5cW6xeKhRwZQR msg_01874ttNreFMGQhhcPZRLFRc

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: 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_011Cc8t4k1tVsEoAbfHQqeL6
O-Max	server: nginx/1.29.8 x-oneapi-request-id: 202606171305567879973348268d9d6fFXAqiXc	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: a0d248113c76e1ee-LAX server: cloudflare x-oneapi-request-id: 2026061721081196604899y2CY91uk	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	a0d248113c76e1ee-LAX
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_011Cc8tJ287mM4aptuHWua5Z

协议指纹评分（机器自动）

总分 / 100 100 86 98 100

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 10.0 /10 ×20 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 10.0 /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 10.0 /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 0.0 /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 10.0 /10 ×5

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

Req-ID 透传 10.0 /10 ×4 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 10.0 /10 ×3

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

流式投递未计入未计入未计入未计入

综合结论

与基线相似度基准（参考） 86 v3.21.0 98 v3.21.0 100 v3.21.0

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 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 5609 ms 8948 ms 3838 ms 4832 ms

输出速度 66.0 tok/s 96.4 tok/s burst 41.1 tok/s

完成步骤 6/6 成功 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 ⓘ

$0.3049

$0.6551

$0.3057

$0.3048

缓存读取占比 ⓘ 71% 52% 71% 71%

揭晓

通道

官方基准

服务商 ByteCatCode ↗

通道O-Max

服务商 PackyCode ↗

通道cc-Zeus

服务商 SAIAi ↗

通道O-Max

返回列表