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

2026/06/23 运行日期

claude-opus-4-8 官方基准

2 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

DBAI / M-
```
评测失败
```

步骤 / 指标

FoxCode

R-ultra

官方基准

HongMaCC

u-cc

FoxCode

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 13:50:19 ~ 13:50:24 (3.9s) 13:50:27 ~ 13:50:32 (4.7s) 13:50:23 ~ 13:50:33 (5.1s) 13:50:21 ~ 13:50:26 (3.6s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,460 ms 3,001 ms 3,744 ms 2,098 ms

首文本(SSE delta) 2,568 ms 3,002 ms 3,745 ms 2,100 ms

总耗时 2,646 ms 3,556 ms 3,746 ms 2,329 ms

输入 37 1,454 2 1,454

输出 2 4 4 4

缓存创建

23,523

5m: 23,523 / 1h: 0

30,222

5m: 0 / 1h: 30,222

31,083

5m: 0 / 1h: 31,083

30,222

5m: 30,222 / 1h: 0

缓存读取 0 0 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 13:54:02 ~ 13:54:07 (4.8s) 13:53:12 ~ 13:53:17 (4.9s) 13:52:35 ~ 13:52:45 (5.6s) 13:53:38 ~ 13:53:48 (5.8s)

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。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) 2,530 ms 3,326 ms 4,350 ms 4,385 ms

首文本(SSE delta) 2,531 ms 3,328 ms 4,351 ms 4,388 ms

总耗时 3,772 ms 3,714 ms 4,352 ms 4,832 ms

输入 32 2 2 2

输出 62 28 28 28

缓存创建

23,726

5m: 23,726 / 1h: 0

1,643

5m: 0 / 1h: 1,643

191

5m: 0 / 1h: 191

1,643

5m: 1,643 / 1h: 0

缓存读取 0 30,222 31,083 30,222

输出速度 50.0 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

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

步骤 3: cutoff text

时间 13:56:10 ~ 13:56:15 (4.2s) 13:55:12 ~ 13:55:18 (3.8s) 13:54:57 ~ 13:55:07 (7.3s) 13:55:14 ~ 13:55:25 (6.5s)

提示词

查看本步 Prompt

Knowledge cutoff date? Reply with YYYY-MM only.

HTTP 头(TTFB) 1,910 ms 2,211 ms 5,967 ms 5,136 ms

首文本(SSE delta) 1,911 ms 2,213 ms 5,968 ms 5,138 ms

总耗时 2,972 ms 2,723 ms 5,968 ms 5,384 ms

输入 32 2 0 2

输出 40 6 32 6

缓存创建

388

5m: 388 / 1h: 0

5m: 0 / 1h: 64

5m: 0 / 1h: 0

5m: 64 / 1h: 0

缓存读取 23,726 31,865 0 31,865

输出速度 37.7 tok/s - burst -

响应

2026-01

2026-01

2026-01

2026-01

步骤 4: identity_free text

时间 13:59:59 ~ 14:00:04 (4.8s) 13:56:35 ~ 13:57:00 (21.4s) 13:57:08 ~ 13:57:18 (7.8s) 13:57:44 ~ 13:57:54 (7.1s)

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) 2,887 ms 19,387 ms 6,661 ms 5,508 ms

首文本(SSE delta) 2,888 ms 19,439 ms 6,662 ms 5,513 ms

总耗时 3,929 ms 20,271 ms 6,662 ms 6,289 ms

输入 62 2 2 2

输出 54 54 67 51

缓存创建

24,469

5m: 24,469 / 1h: 0

5m: 0 / 1h: 37

5m: 0 / 1h: 97

5m: 37 / 1h: 0

缓存读取 0 31,929 31,274 31,929

输出速度 51.9 tok/s 64.9 tok/s burst 65.7 tok/s

响应

我是 Claude，由 Anthropic 打造的 AI 助手，当前运行的模型为 claude-opus-4-8。

我叫 Claude，是 Anthropic 开发的 AI 助手，属于 Claude 系列产品，当前模型为 Opus 4.8。

我是 Claude Code，Anthropic 公司打造的官方命令行 AI 编程助手，基于 Claude Opus 4.8 模型，帮助用户完成软件工程任务。

我是 Claude，属于 Claude 产品系列，由 Anthropic 公司开发。具体型号为 Claude Opus 4.8。

步骤 5: knowledge_recall text

时间 14:01:23 ~ 14:01:48 (24.4s) 13:58:20 ~ 13:58:40 (15.2s) 13:59:32 ~ 13:59:47 (13.5s) 14:01:42 ~ 14:01:52 (8.5s)

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) 1,462 ms 8,580 ms 12,340 ms 1,729 ms

首文本(SSE delta) 1,463 ms 11,834 ms 12,341 ms 5,026 ms

总耗时 23,544 ms 14,158 ms 12,342 ms 7,372 ms

输入 62 2 2 2

输出 1,865 696 691 697

缓存创建

4,666

5m: 4,666 / 1h: 0

4,774

5m: 0 / 1h: 4,774

3,734

5m: 0 / 1h: 3,734

4,771

5m: 4,771 / 1h: 0

缓存读取 0 0 15,933 0

输出速度 84.5 tok/s burst 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 14:05:02 ~ 14:05:27 (20.2s) 14:00:55 ~ 14:01:05 (5.5s) 14:01:44 ~ 14:01:59 (11.1s) 14:03:03 ~ 14:03:43 (36.1s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=976094067689190174067665996457986926040820577803898754962376485336861900

HTTP 头(TTFB) 2,055 ms 3,885 ms 9,329 ms 34,107 ms

首文本(SSE delta) 2,056 ms 4,060 ms 9,330 ms 34,240 ms

总耗时 19,151 ms 4,545 ms 9,527 ms 35,064 ms

输入 76 211 0 211

输出 2,030 19 1,270 19

缓存创建

134

5m: 134 / 1h: 0

5m: 0 / 1h: 0

缓存读取 0 0 0 0

输出速度 118.7 tok/s - burst -

响应

```
s = "976094067689190174067665996457986926040820577803898754962376485336861900"
```

Counting digit by digit:

n = 72

0s at positions: 4,7,15,19,37,39,42,47,71,72 → **10**
7s at positions: 2,9,17,

{"n":72,"c":[10,7,12]}

{"n":72,"c":[10,9,11]}

{"n":72,"c":[10,7,12]}

总计

总输入(含缓存) 100,933 132,429 113,403 132,426

总输出 4,053 807 2,092 805

总缓存创建

76,906

5m: 76,906 / 1h: 0

36,740

5m: 0 / 1h: 36,740

35,105

5m: 0 / 1h: 35,105

36,737

5m: 36,737 / 1h: 0

总缓存读取 23,726 94,016 78,290 94,016

输出速度 95.3 tok/s 64.9 tok/s burst 65.7 tok/s

总执行时间 1m 2.3s 55.6s 50.4s 1m 7.6s

总墙钟时间

15m 8.1s

含步骤间等待

10m 38.0s

含步骤间等待

11m 36.2s

含步骤间等待

13m 22.1s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.4151

Anthropic: Claude Opus 4.8

$0.3052

Anthropic: Claude Opus 4.8

>=$0.3109

Anthropic: Claude Opus 4.8 (成本不完整)

$0.2190

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count digit_count digit_count digit_count

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

ID 格式 msg_01Z2n3ebDj7GEE37zdmltmkk msg_017p6XvHx2hTMh4d7ztm1Y9k msg_b46207c0fb70d0d362c98f54 msg_01CcGju9wwAm2MAvNkJ9WYLS

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
R-ultra	cf-ray: a1014c817c96734b-NRT server: cloudflare x-new-api-version: v0.0.0 x-oneapi-request-id: 202606230605037689114038268d9d67oairhBT	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	a1014c817c96734b-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_011CcKgWyPv1C7xV5rtphMsJ
u-cc	server: nginx x-new-api-version: 1.0.14 x-oneapi-request-id: 202606230601462769639258268d9d6oAi6QGHD	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-new-api-versionhdr:x-oneapi-request-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
cc	cf-ray: a101499a19df734b-NRT server: cloudflare set-cookie: _cfuvid=lDl7cEHZ1csPJ8eqXXzBVzRy1QKHAFXMkPr4e76raLc-1782194584.9867167-1.0.1.1-or2EGyyFdGz0Rvn2QtCG3AEdUbvIw6pxoTo3IiYz8N8; 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	hdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_011CcKggRpQ8osTiys3AdxJ9 a101499a19df734b-NRT

协议指纹评分（机器自动）

总分 / 100 64 100 77 91

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

缓存 TTL 一致 0.0 /10 ×15 10.0 /10 ×15 7.0 /10 ×15 0.0 /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 6.7 /10 ×14 10.0 /10 ×14

sliding 5m 5.3 /10 ×13 10.0 /10 ×13 4.7 /10 ×13 10.0 /10 ×13

原生 msg-ID 10.0 /10 ×8 10.0 /10 ×8 7.0 /10 ×8 10.0 /10 ×8

系统提示纯净 0.0 /10 ×8 10.0 /10 ×8 5.0 /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 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 10.0 /10 ×5

延迟基线 10.0 /10 ×5 10.0 /10 ×5 7.3 /10 ×5 8.8 /10 ×5

流式投递 8.0 /10 ×5 10.0 /10 ×5 0.0 /10 ×5 10.0 /10 ×5

Req-ID 透传 0.0 /10 ×4 10.0 /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

综合结论

与基线相似度 64 v3.24.0 基准（参考） 77 v3.24.0 91 v3.24.0

雷达图例

共 23 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 自报身份一致 self_identity_consistency
20 信封自报一致 envelope_self_report_match
21 中文遵循 instruction_following_lang
22 档位思考量 tier_thinking_volume_match
23 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 9336 ms 8161 ms 7100 ms 10212 ms

输出速度 95.3 tok/s 64.9 tok/s burst 65.7 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 ⓘ

$0.4151

$0.3052

>=$0.3109 (成本不完整)

$0.2190

缓存读取占比 ⓘ 24% 71% 69% 71%

揭晓

通道

服务商 FoxCode ↗

通道R-ultra

官方基准

服务商 HongMaCC ↗

通道u-cc

服务商 FoxCode ↗

通道cc

返回列表