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

2026/06/22 运行日期

claude-opus-4-8 官方基准

1 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

InfAI / R-Kiro
```
评测失败
```
Aiberm / cc
```
评测失败
```

步骤 / 指标

duckcoding

cc专用

FoxCode

R-ultra

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 14:39:19 ~ 14:39:24 (3.4s) 14:39:15 ~ 14:39:20 (3.9s) 14:39:21 ~ 14:39:26 (3.0s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 1,773 ms 2,519 ms 1,837 ms

首文本(SSE delta) 1,774 ms 2,642 ms 1,840 ms

总耗时 1,996 ms 2,833 ms 1,954 ms

输入 1,454 59 1,454

输出 4 2 4

缓存创建

30,223

5m: 0 / 1h: 30,223

23,501

5m: 23,501 / 1h: 0

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 14:40:33 ~ 14:40:43 (5.0s) 14:40:30 ~ 14:40:40 (5.3s) 14:42:36 ~ 14:42:41 (3.7s)

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) 3,182 ms 2,479 ms 2,106 ms

首文本(SSE delta) 3,206 ms 2,481 ms 2,107 ms

总耗时 3,662 ms 4,316 ms 2,392 ms

输入 2 59 2

输出 28 64 28

缓存创建

1,646

5m: 0 / 1h: 1,646

206

5m: 206 / 1h: 0

1,646

5m: 0 / 1h: 1,646

缓存读取 30,223 23,501 30,222

输出速度 - 34.9 tok/s -

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

步骤 3: cutoff text

时间 14:43:24 ~ 14:43:30 (4.8s) 14:42:34 ~ 14:42:39 (2.9s) 14:44:14 ~ 14:44:19 (4.6s)

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) 3,582 ms 1,721 ms 3,280 ms

首文本(SSE delta) 3,584 ms 1,722 ms 3,281 ms

总耗时 3,761 ms 2,116 ms 3,599 ms

输入 2 15 2

输出 6 11 6

缓存创建

5m: 0 / 1h: 62

24,156

5m: 24,156 / 1h: 0

5m: 0 / 1h: 54

缓存读取 31,869 0 31,868

响应

2025-01

2026-01

2026-01

步骤 4: identity_free text

时间 14:46:08 ~ 14:46:23 (13.2s) 14:46:36 ~ 14:46:41 (4.6s) 14:47:11 ~ 14:47:16 (3.6s)

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) 5,323 ms 1,854 ms 1,756 ms

首文本(SSE delta) 5,553 ms 1,855 ms 1,758 ms

总耗时 11,943 ms 3,711 ms 2,495 ms

输入 2 62 2

输出 56 73 61

缓存创建

5m: 0 / 1h: 37

24,457

5m: 24,457 / 1h: 0

5m: 0 / 1h: 39

缓存读取 31,931 0 31,922

输出速度 8.8 tok/s 39.3 tok/s 82.8 tok/s

响应

我叫 Claude，是 Anthropic 公司开发的 AI 模型，属于 Claude 系列产品，当前型号为 Opus 4.8。

我是 Kiro，一个由 Anthropic 开发的 AI 助手，基于 Claude 模型构建，专注于帮助用户完成软件工程及各类专业任务。

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。

步骤 5: knowledge_recall text

时间 14:49:09 ~ 14:49:19 (6.8s) 14:50:33 ~ 14:51:03 (25.4s) 14:50:23 ~ 14:50:38 (10.1s)

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) 2,100 ms 1,276 ms 3,528 ms

首文本(SSE delta) 2,736 ms 1,277 ms 6,277 ms

总耗时 5,495 ms 24,338 ms 8,929 ms

输入 2 14 2

输出 381 1,999 665

缓存创建

4,778

5m: 0 / 1h: 4,778

4,733

5m: 4,733 / 1h: 0

4,776

5m: 0 / 1h: 4,776

缓存读取 0 0 0

输出速度 138.1 tok/s 86.7 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

步骤 6: digit_count text

时间 14:50:48 ~ 14:50:53 (4.8s) 14:52:27 ~ 14:52:52 (21.2s) 14:51:53 ~ 14:51:58 (2.8s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=990482231789461952864813782958557634332512460169829309520079276783043802

HTTP 头(TTFB) 2,734 ms 1,701 ms 1,531 ms

首文本(SSE delta) 2,922 ms 1,701 ms 1,532 ms

总耗时 3,522 ms 20,070 ms 1,843 ms

输入 212 14 211

输出 19 2,434 19

缓存创建

5m: 0 / 1h: 0

197

5m: 197 / 1h: 0

5m: 0 / 1h: 0

缓存读取 0 0 0

输出速度 - 132.5 tok/s -

响应

{"n":70,"c":[7,5,11]}

{"n":72,"c":[7,6,9]}

{"n":70,"c":[7,5,9]}

总计

总输入(含缓存) 132,443 100,974 132,422

总输出 494 4,583 783

总缓存创建

36,746

5m: 0 / 1h: 36,746

77,250

5m: 77,250 / 1h: 0

36,737

5m: 0 / 1h: 36,737

总缓存读取 94,023 23,501 94,012

输出速度 47.8 tok/s 101.3 tok/s 82.8 tok/s

总执行时间 38.1s 1m 3.2s 27.8s

总墙钟时间

11m 34.0s

含步骤间等待

13m 37.2s

含步骤间等待

12m 37.1s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.2974

Anthropic: Claude Opus 4.8

$0.4292

Anthropic: Claude Opus 4.8

$0.3046

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count digit_count digit_count

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

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

CDN - cloudflare -

ID 格式 msg_012hzUak6pPeW8o4PBRD8wJ5 msg_01wP770FjhOXlLQxEsw8z8S2 msg_01Ma3Uwu3hrVYZg26fRRLo6V

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

cc专用

server: Nginx
x-oneapi-request-id: 20260622065051797171718268d9d6PRwQVlAr

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

—

R-ultra

cf-ray: a0f95497ce9f7963-NRT
server: cloudflare
x-new-api-version: v0.0.0
x-oneapi-request-id: 202606220652289350273538268d9d66cwrfgN8

id_format: msg_prefix
has_service_tier: true
has_inference_geo: true
model_has_date_suffix: false
usage_has_cache_fields: true

hdr:x-new-api-versionhdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsupstream:anthropic-direct-from-body

a0f95497ce9f7963-NRT

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_011CcHrbUxvgMdqVHRBfKuHt

协议指纹评分（机器自动）

总分 / 100 91 57 100

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 0.0 /10 ×20 10.0 /10 ×20

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

sliding 5m 10.0 /10 ×13 0.0 /10 ×13 10.0 /10 ×13

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

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

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

知识截止 0.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7

身份(自由) 10.0 /10 ×7 0.0 /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 10.0 /10 ×5 10.0 /10 ×5

流式投递 10.0 /10 ×5 7.8 /10 ×5 10.0 /10 ×5

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

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

综合结论

与基线相似度 91 v3.24.0 57 v3.24.0 基准（参考）

雷达图例

共 22 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 中文遵循 instruction_following_lang
21 档位思考量 tier_thinking_volume_match
22 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 5063 ms 9564 ms 3535 ms

输出速度 47.8 tok/s 101.3 tok/s 82.8 tok/s

完成步骤 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 ⓘ

$0.2974

$0.4292

$0.3046

缓存读取占比 ⓘ 71% 23% 71%

揭晓

通道

服务商 duckcoding ↗

通道cc专用

服务商 FoxCode ↗

通道R-ultra

官方基准

返回列表