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。

5 通道 · 6 步骤

2026/06/22 运行日期

claude-haiku-4-5-20251001 官方基准

2 通道分数 < 70 与基线相似度

已揭晓揭晓进度

步骤 / 指标

PackyCode

cc-Zeus

官方基准

FoxCode

SSSAiCode

R-Kiro

SSSAiCode

O-Max-L2

基本信息

服务名 Claude Code Claude Code Claude Code Claude Code Claude Code

模型 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001

客户端 claude-cli v2.1.160 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 03:22:52 ~ 03:22:57 (3.2s) 03:22:56 ~ 03:23:01 (4.2s) 03:22:48 ~ 03:22:53 (3.8s) 03:22:54 ~ 03:22:59 (4.1s) 03:22:50 ~ 03:22:55 (3.4s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 1,673 ms 2,439 ms 2,446 ms 2,871 ms 2,020 ms

首文本(SSE delta) 1,677 ms 2,440 ms 2,447 ms 2,886 ms 2,383 ms

总耗时 2,181 ms 3,133 ms 2,907 ms 3,253 ms 2,432 ms

输入 10 10 10 0 10

输出 57 65 47 68 47

缓存创建

33,122

5m: 0 / 1h: 33,122

33,122

5m: 0 / 1h: 33,122

33,122

5m: 33,122 / 1h: 0

32,785

5m: 0 / 1h: 32,785

缓存读取 0 0 0 0 0

输出速度 113.1 tok/s 93.8 tok/s 102.2 tok/s 185.3 tok/s burst

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 03:24:45 ~ 03:24:56 (5.4s) 03:26:06 ~ 03:26:16 (5.1s) 03:25:17 ~ 03:25:22 (4.3s) 03:26:08 ~ 03:26:13 (4.9s) 03:24:42 ~ 03:24:57 (10.4s)

提示词

查看本步 Prompt

以下是对你自身的 metadata 探针。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。按以下 3 行回答自己的身份，每行一个 label，不要寒暄不要解释：
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) 2,181 ms 1,759 ms 1,796 ms 2,327 ms 1,447 ms

首文本(SSE delta) 2,201 ms 1,761 ms 1,797 ms 2,342 ms 9,408 ms

总耗时 4,047 ms 4,068 ms 3,515 ms 3,969 ms 9,623 ms

输入 10 10 10 0 10

输出 230 206 194 191 603

缓存创建

261

5m: 0 / 1h: 261

269

5m: 0 / 1h: 269

202

5m: 202 / 1h: 0

251

5m: 0 / 1h: 251

缓存读取 33,122 33,122 33,122 0 32,785

输出速度 124.6 tok/s 89.3 tok/s 112.9 tok/s 117.4 tok/s burst

响应

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

vendor: anthropic
brand: claude
model: unknown

步骤 3: cutoff text

时间 03:27:19 ~ 03:27:24 (3.0s) 03:29:00 ~ 03:29:05 (3.3s) 03:26:29 ~ 03:26:34 (3.7s) 03:27:58 ~ 03:28:03 (3.7s) 03:27:38 ~ 03:27:43 (2.9s)

提示词

查看本步 Prompt

Knowledge cutoff date? Reply with YYYY-MM only.

HTTP 头(TTFB) 1,484 ms 1,665 ms 1,951 ms 2,319 ms 1,611 ms

首文本(SSE delta) 1,488 ms 1,666 ms 1,952 ms 2,322 ms 2,148 ms

总耗时 2,054 ms 2,272 ms 2,595 ms 2,901 ms 2,188 ms

输入 10 10 10 0 10

输出 66 64 83 71 91

缓存创建

253

5m: 0 / 1h: 253

246

5m: 0 / 1h: 246

5m: 61 / 1h: 0

645

5m: 0 / 1h: 645

缓存读取 33,383 33,391 33,324 0 33,036

输出速度 116.6 tok/s 105.6 tok/s 129.1 tok/s 122.6 tok/s burst

响应

2025-02

2025-02

2025-02

2025-02

2024-04

步骤 4: identity_free text

时间 03:30:20 ~ 03:30:35 (10.2s) 03:32:55 ~ 03:33:05 (5.4s) 03:28:01 ~ 03:28:11 (5.0s) 03:31:38 ~ 03:31:43 (4.5s) 03:29:03 ~ 03:29:08 (4.6s)

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) 1,491 ms 2,133 ms 2,392 ms 2,315 ms 1,595 ms

首文本(SSE delta) 1,492 ms 2,134 ms 2,393 ms 2,333 ms 3,468 ms

总耗时 9,175 ms 4,388 ms 3,780 ms 3,570 ms 3,738 ms

输入 10 10 10 0 10

输出 1,214 333 195 113 323

缓存创建

104

5m: 0 / 1h: 104

5m: 0 / 1h: 98

5m: 43 / 1h: 0

129

5m: 0 / 1h: 129

缓存读取 33,636 33,637 33,385 0 33,681

输出速度 158.0 tok/s 147.7 tok/s 140.6 tok/s 91.4 tok/s -

响应

我是Anthropic的Claude Haiku模型，一个AI编码助手，可协助代码编写、调试和重构。

我是Claude，由Anthropic公司开发的AI助手。我可以帮助进行软件工程相关的工作，包括代码编写、调试、测试等任务。

我是Claude，由Anthropic公司开发的AI助手。我可以帮助进行对话、代码编程、文本分析、创意写作等多种任务。

我是Claude，由Anthropic公司开发的AI助手。我是Claude Haiku 4.5模型，可以帮助编程、分析、写作等多项任务。我遵循安全准则，致力于提供有帮助且诚实的回复。

我是Claude，由美国AI安全公司Anthropic开发的AI助手。我可以帮助用户完成各种任务，包括代码编写、分析、创意写作和问题解答。

步骤 5: knowledge_recall text

时间 03:34:15 ~ 03:34:35 (16.0s) 03:34:06 ~ 03:34:26 (17.3s) 03:29:26 ~ 03:30:16 (47.5s) 03:33:40 ~ 03:34:00 (18.0s) 03:31:36 ~ 03:31:46 (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) 1,238 ms 1,354 ms 1,525 ms 1,857 ms 1,401 ms

首文本(SSE delta) 1,240 ms 1,356 ms 1,526 ms 1,883 ms 7,349 ms

总耗时 14,830 ms 16,336 ms 46,760 ms 17,267 ms 7,535 ms

输入 10 10 10 0 10

输出 2,263 2,440 3,934 2,897 1,125

缓存创建

9,572

5m: 0 / 1h: 9,572

8,686

5m: 0 / 1h: 8,686

8,091

5m: 8,091 / 1h: 0

8,751

5m: 0 / 1h: 8,751

缓存读取 0 0 0 0 0

输出速度 166.5 tok/s 162.9 tok/s 87.0 tok/s 188.3 tok/s burst

响应

```json
{"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

```json
{"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

```json
{"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

```json
{"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

```json
{"facts":{"super_bowl_lviii":"Kansas City Chiefs","oscars2024_best_picture":"Oppenheimer","ucl_2024":"UNKNOWN","nba_2024":"UNKNOWN","copa_america_2024":"UNKNOWN","euro2024":"UNKNOWN","nobel_pe

步骤 6: digit_count text

时间 03:37:32 ~ 03:37:47 (14.0s) 03:37:40 ~ 03:38:00 (18.5s) 03:32:03 ~ 03:32:38 (30.5s) 03:36:31 ~ 03:36:46 (12.1s) 03:34:52 ~ 03:35:07 (11.9s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=563920782463342745547484602116651322539218330545750747312651854320410332

HTTP 头(TTFB) 734 ms 1,242 ms 1,310 ms 1,377 ms 806 ms

首文本(SSE delta) 735 ms 1,243 ms 1,312 ms 1,386 ms 808 ms

总耗时 12,892 ms 17,464 ms 29,629 ms 11,194 ms 11,005 ms

输入 193 193 193 0 139

输出 2,189 3,016 2,697 1,573 1,757

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0 0

输出速度 180.1 tok/s 185.9 tok/s 95.2 tok/s 160.4 tok/s 172.3 tok/s

响应

```json
{"n":72,"c":[6,6,2]}
```

```json
{"n":72,"c":[6,6,2]}
```

```json
{"n":72,"c":[6,6,2]}
```

```json
{"n":72,"c":[6,6,2]}
```

```json
{"n":72,"c":[6,6,2]}
```

总计

总输入(含缓存) 143,696 142,814 141,593 0 142,252

总输出 6,019 6,124 7,150 4,913 3,946

总缓存创建

43,312

5m: 0 / 1h: 43,312

42,421

5m: 0 / 1h: 42,421

41,519

5m: 41,519 / 1h: 0

42,561

5m: 0 / 1h: 42,561

总缓存读取 100,141 100,150 99,831 0 99,502

输出速度 165.6 tok/s 165.2 tok/s 92.0 tok/s 169.4 tok/s 172.3 tok/s

总执行时间 51.7s 53.9s 1m 34.8s 47.3s 41.5s

总墙钟时间

14m 55.0s

含步骤间等待

15m 4.1s

含步骤间等待

9m 50.1s

含步骤间等待

13m 51.4s

含步骤间等待

12m 17.1s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.0945

Anthropic: Claude Haiku 4.5

$0.0939

Anthropic: Claude Haiku 4.5

$0.0784

Anthropic: Claude Haiku 4.5

>=$0.0246

Anthropic: Claude Haiku 4.5 (成本不完整)

$0.0831

Anthropic: Claude Haiku 4.5

通道指纹

来源步骤 digit_count digit_count digit_count digit_count digit_count

平台 one-api (100%) direct (100%) direct (100%) direct (75%) direct (100%)

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

CDN cloudflare - cloudflare - -

ID 格式 msg_01JKppZFnmfCZpjpejDkU8Q6 msg_017dRvCKFe2nevGMbzoZE1eS msg_01KRSF76scqVH5ezc6V2JUSa msg_dc1aafe730814a0b84894f644e45d08a msg_011jhPM87UaBStHSgwVubzHr

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-Zeus	via: 1.1 Caddy cf-ray: a0f577f28e923105-LAX server: cloudflare x-oneapi-request-id: 202606220337338681154894OtgMHQU	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: true usage_has_cache_fields: true	hdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-rayhdr:viabody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a0f577f28e923105-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: true usage_has_cache_fields: true	body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_011CcGyBY6LkcxEkHa1MdqVt
cc	cf-ray: a0f56fe9aacf734b-NRT server: cloudflare set-cookie: _cfuvid=mODLT6uQ9FhdFU9Ny8kEA1_W_5VbKu7BrcKyjKkuDzg-1782070325.1049194-1.0.1.1-B6FaPqXS33EYja.qURTi4cn85PkpNVsWYNMVNoT7Eyw; 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: true usage_has_cache_fields: true	hdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_011CcGxkhJ38Y17H4RdWG9sH a0f56fe9aacf734b-NRT
R-Kiro	server: Photon-Edge x-amzn-requestid: bc7072a6-b816-4e42-be47-b2540c907bd7	id_format: msg_prefix has_service_tier: false has_inference_geo: false model_has_date_suffix: false usage_has_cache_fields: true	body:id:msg_prefixbody:usage.cache_fieldsupstream:x-amzn-requestidupstream:anthropic-direct-from-body	1782070592186-kvpdii9z6hgh6 bc7072a6-b816-4e42-be47-b2540c907bd7
O-Max-L2	cf-ray: a0f5740a89f5dcfa-LAX server: Photon-Edge set-cookie: _cfuvid=UfDMNFCuOP50qSZcoiGLVy8wjQnNnswG5EOa6gVECI0-1782070493.8479462-1.0.1.1-325jeytisikx7G9q4Iq_GjgDonkC1l1W96efR3HgGV4; 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: true usage_has_cache_fields: true	body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	1782070493799-3pjtxq8q6fl19 req_011CcGxy8nJ4kyqRNZTPZ1S1 a0f5740a89f5dcfa-LAX

协议指纹评分（机器自动）

总分 / 100 98 100 91 54 84

基线状态已对照基线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 0.0 /10 ×20 10.0 /10 ×20

缓存 TTL 一致 10.0 /10 ×15 10.0 /10 ×15 0.0 /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 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 5.0 /10 ×14 10.0 /10 ×14

sliding 5m 10.0 /10 ×13 10.0 /10 ×13 10.0 /10 ×13 5.0 /10 ×13 10.0 /10 ×13

原生 msg-ID 10.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8 0.0 /10 ×8 10.0 /10 ×8

系统提示纯净 10.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8 未计入 5.0 /10 ×8

身份(结构) 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 6.7 /10 ×7

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

身份(自由) 10.0 /10 ×7 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 0.0 /10 ×6 10.0 /10 ×6

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

Req-ID 透传 0.0 /10 ×4 10.0 /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 10.0 /10 ×3

SDK 一致 10.0 /10 ×2 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未计入

综合结论

与基线相似度 98 v3.24.0 基准（参考） 91 v3.24.0 54 v3.24.0 84 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 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 Thinking 体量 thinking_volume_match
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 7530 ms 7944 ms 14864 ms 7026 ms 6087 ms

输出速度 165.6 tok/s 165.2 tok/s 92.0 tok/s 169.4 tok/s 172.3 tok/s

完成步骤 6/6 成功 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 ⓘ

$0.0945

$0.0939

$0.0784

>=$0.0246 (成本不完整)

$0.0831

缓存读取占比 ⓘ 70% 70% 71% - 70%

揭晓

通道

服务商 PackyCode ↗

通道cc-Zeus

官方基准

服务商 FoxCode ↗

通道cc

服务商 SSSAiCode ↗

通道R-Kiro

服务商 SSSAiCode ↗

通道O-Max-L2

返回列表