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

2026/07/02 运行日期

claude-haiku-4-5-20251001 官方基准

1 通道分数 < 70 与基线相似度

已揭晓揭晓进度

步骤 / 指标

LinkAPI

O-Max

WorldBase.ai

M-

LingxiCode

M-

官方基准

OmniaKey

O-Max

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 v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195

偏差标红基于官方基准

步骤 1: ping text

时间 10:46:50 ~ 10:47:00 (6.2s) 10:46:52 ~ 10:47:02 (7.0s) 10:46:54 ~ 10:46:59 (4.0s) 10:46:56 ~ 10:47:02 (3.6s) 10:46:48 ~ 10:46:53 (4.7s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 4,728 ms 5,318 ms 2,544 ms 2,100 ms 3,013 ms

首文本(SSE delta) 4,730 ms 5,390 ms 2,545 ms 2,107 ms 3,014 ms

总耗时 5,143 ms 5,801 ms 3,196 ms 2,587 ms 3,525 ms

输入 10 14 10 10 10

输出 54 69 61 53 58

缓存创建

6,166

5m: 0 / 1h: 6,166

21,298

5m: 0 / 1h: 21,298

6,288

5m: 0 / 1h: 6,165

6,166

5m: 0 / 1h: 6,166

6,166

5m: 0 / 1h: 6,166

缓存读取 15,379 0 15,686 15,379 15,379

输出速度 130.8 tok/s 167.9 tok/s 93.7 tok/s 110.4 tok/s 113.5 tok/s

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 10:49:43 ~ 10:49:53 (5.3s) 10:48:52 ~ 10:49:17 (22.2s) 10:48:20 ~ 10:48:30 (6.0s) 10:49:49 ~ 10:49:59 (5.5s) 10:48:22 ~ 10:48:32 (7.8s)

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。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) 2,352 ms 14,606 ms 2,676 ms 2,573 ms 3,250 ms

首文本(SSE delta) 2,353 ms 20,514 ms 2,689 ms 2,575 ms 3,251 ms

总耗时 4,191 ms 21,072 ms 5,229 ms 4,524 ms 5,692 ms

输入 10 240 10 10 10

输出 216 206 273 167 213

缓存创建

248

5m: 0 / 1h: 248

21,395

5m: 0 / 1h: 21,395

260

5m: 0 / 1h: 255

247

5m: 0 / 1h: 247

252

5m: 0 / 1h: 252

缓存读取 21,545 0 21,974 21,545 21,545

输出速度 117.5 tok/s - 107.5 tok/s 85.7 tok/s 87.3 tok/s

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: claude-haiku-4-5-20251001

步骤 3: cutoff text

时间 10:51:57 ~ 10:52:07 (6.3s) 10:52:36 ~ 10:52:46 (8.9s) 10:49:58 ~ 10:50:03 (3.8s) 10:52:12 ~ 10:52:17 (3.6s) 10:50:31 ~ 10:50:36 (4.7s)

提示词

查看本步 Prompt

Knowledge cutoff date? Reply with YYYY-MM only.

HTTP 头(TTFB) 4,708 ms 5,920 ms 2,321 ms 1,842 ms 3,018 ms

首文本(SSE delta) 4,710 ms 5,921 ms 2,325 ms 1,844 ms 3,019 ms

总耗时 5,342 ms 6,659 ms 3,062 ms 2,534 ms 3,666 ms

输入 10 37 10 10 10

输出 64 5 61 67 62

缓存创建

239

5m: 0 / 1h: 239

23,819

5m: 0 / 1h: 23,819

301

5m: 0 / 1h: 296

209

5m: 0 / 1h: 209

236

5m: 0 / 1h: 236

缓存读取 21,793 0 22,234 21,792 21,797

输出速度 101.3 tok/s - 82.8 tok/s 97.1 tok/s 95.8 tok/s

响应

2025-02


2025-02

2025-02

2025-02

2025-02

步骤 4: identity_free text

时间 10:55:09 ~ 10:55:14 (4.2s) 10:55:14 ~ 10:55:25 (7.4s) 10:52:16 ~ 10:52:31 (10.6s) 10:53:39 ~ 10:53:49 (9.4s) 10:52:46 ~ 10:53:16 (25.1s)

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) 1,812 ms 3,392 ms 1,953 ms 1,571 ms 3,913 ms

首文本(SSE delta) 1,813 ms 3,393 ms 1,955 ms 1,572 ms 4,973 ms

总耗时 2,970 ms 6,325 ms 9,669 ms 8,475 ms 23,937 ms

输入 10 41 10 10 10

输出 152 55 1,201 728 2,158

缓存创建

106

5m: 0 / 1h: 106

157

5m: 0 / 1h: 157

103

5m: 0 / 1h: 101

109

5m: 0 / 1h: 109

104

5m: 0 / 1h: 104

缓存读取 22,032 23,808 22,536 22,001 22,033

输出速度 131.4 tok/s 18.8 tok/s 155.7 tok/s 105.5 tok/s 113.8 tok/s

响应

我是Claude，由Anthropic开发的AI助手。我是Haiku 4.5模型，可以帮助编程、分析、写作等多种任务。我设计用来与用户进行有帮助、诚实和无害的对话。


我是Claude，由Anthropic开发的AI助手。我专于软件工程，可帮助代码编写、调试和分析。通过Claude Code开发环境与用户交互。

我叫Claude Haiku 4.5，属于Claude产品线，由Anthropic公司开发。是一款轻量级的AI助手，擅长代码编写、分析和工程任务协作。

我是Claude Code，由Anthropic开发的AI助手。帮助用户处理软件工程任务，如代码编写、调试、测试和代码审查。

我是Claude，Anthropic公司开发的AI助手。擅长代码编写、问题分析和技术咨询，可协助软件开发、调试等工作。

步骤 5: knowledge_recall text

时间 10:56:58 ~ 10:57:23 (24.4s) 10:57:22 ~ 10:57:47 (23.6s) 10:55:00 ~ 10:55:15 (13.6s) 10:54:57 ~ 10:55:32 (31.9s) 10:54:29 ~ 10:55:14 (42.7s)

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) 1,700 ms 2,726 ms 1,818 ms 1,451 ms 2,504 ms

首文本(SSE delta) 1,701 ms 2,727 ms 1,819 ms 1,453 ms 2,504 ms

总耗时 23,372 ms 22,574 ms 12,757 ms 30,921 ms 41,570 ms

输入 10 1,005 10 10 10

输出 1,858 180 2,021 3,217 4,460

缓存创建

9,241

5m: 0 / 1h: 9,241

10,190

5m: 0 / 1h: 10,190

10,554

5m: 0 / 1h: 10,348

9,789

5m: 0 / 1h: 9,789

11,246

5m: 0 / 1h: 11,246

缓存读取 0 0 0 0 0

输出速度 85.7 tok/s 9.1 tok/s 184.8 tok/s 109.2 tok/s 114.2 tok/s

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":"Spa

```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

步骤 6: digit_count text

时间 10:59:53 ~ 11:00:23 (26.7s) 11:00:19 ~ 11:00:39 (15.6s) 10:59:11 ~ 10:59:41 (26.2s) 10:59:28 ~ 10:59:43 (14.5s) 10:56:53 ~ 10:57:24 (26.3s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=304545951114521209754092258490784231390307169614882837806570308528896589

HTTP 头(TTFB) 1,348 ms 2,535 ms 1,362 ms 840 ms 1,737 ms

首文本(SSE delta) 1,350 ms 2,536 ms 1,363 ms 841 ms 1,738 ms

总耗时 25,770 ms 14,531 ms 25,427 ms 13,638 ms 25,339 ms

输入 2,034 66 196 193 193

输出 2,962 3,264 3,696 2,376 4,758

缓存创建

5m: 0 / 1h: 0

444

5m: 634 / 1h: 0

5m: 0 / 1h: 0

缓存读取 0 284 0 0 0

输出速度 121.3 tok/s burst 153.6 tok/s 185.7 tok/s 201.6 tok/s

响应

```json
{"n":72,"c":[9,5,8]}
```

```json
{"n":72,"c":[9,5,8]}
```

```json
{"n":72,"c":[9,5,8]}
```

```json
{"n":72,"c":[9,5,8]}
```

```json
{"n":72,"c":[9,5,8]}
```

总计

总输入(含缓存) 98,833 102,798 100,182 97,480 99,001

总输出 5,306 3,779 7,313 6,608 11,709

总缓存创建

16,000

5m: 0 / 1h: 16,000

77,303

5m: 634 / 1h: 76,859

17,506

5m: 0 / 1h: 17,165

16,520

5m: 0 / 1h: 16,520

18,004

5m: 0 / 1h: 18,004

总缓存读取 80,749 24,092 82,430 80,717 80,754

输出速度 105.8 tok/s 13.1 tok/s 156.8 tok/s 126.4 tok/s 137.4 tok/s

总执行时间 1m 13.0s 1m 24.7s 1m 4.3s 1m 8.5s 1m 51.4s

总墙钟时间

13m 33.1s

含步骤间等待

13m 46.6s

含步骤间等待

12m 47.0s

含步骤间等待

12m 46.2s

含步骤间等待

10m 35.2s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.0567

Anthropic: Claude Haiku 4.5

$0.1193

Anthropic: Claude Haiku 4.5

$0.0665

Anthropic: Claude Haiku 4.5

$0.0620

Anthropic: Claude Haiku 4.5

$0.0894

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

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

CDN - cloudflare cloudflare - cloudflare

ID 格式 msg_01DonedjRDmRLbqvbqq1E6Dc msg_01bDPNzy6icgCdxf4G8Y8PAg msg_01VXTd3tKqyP9VWb9R5rNKCG msg_01BMx1qMD7JC5vG451K8DU3N msg_01BCi5jqkoDhMEgdryD7xP8s

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	server: nginx set-cookie: server_name_session=c576e09cb6f84c78844c48bf7e3b48cb; Max-Age=86400; httponly; path=/ x-new-api-version: v1.0.0-rc.15 x-oneapi-request-id: 202607020259548860289828268d9d6ffpyHO0Z	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:x-new-api-versionhdr:x-oneapi-request-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
M-	cf-ray: a14a664cbb3bb1fb-AMS server: cloudflare	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	047b5d25-24e1-4b4c-a49d-efadd2ed6b35 a14a664cbb3bb1fb-AMS
M-	cf-ray: a14a64a39bfffd4f-NRT server: cloudflare set-cookie: server_name_session=8100cd3b152282d126debf79c7d0b8f6; Max-Age=86400; httponly; path=/ x-oneapi-request-id: 202607020259127029237817gfkWFZx	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:x-oneapi-request-idhdr: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	a14a64a39bfffd4f-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: 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_011CccUxe1EzyrNcak4Pw6Aa
O-Max	cf-ray: a14a6147ef076699-AMS server: cloudflare x-oneapi-request-id: 202607020256555039115308268d9d6oRIz4e6N	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:x-oneapi-request-idhdr: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	a14a6147ef076699-AMS

协议指纹评分（机器自动）

总分 / 100 97 70 96 100 98

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 0.0 /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 10.0 /10 ×15

延迟基线 7.9 /10 ×15 2.7 /10 ×15 10.0 /10 ×15 10.0 /10 ×15 9.8 /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 10.0 /10 ×14 10.0 /10 ×14

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

原生 msg-ID 10.0 /10 ×8 4.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8

系统提示纯净 10.0 /10 ×8 5.0 /10 ×8 5.0 /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 10.0 /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 10.0 /10 ×6 10.0 /10 ×6

知识截止 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

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

stop_reason 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3

Req-ID 透传 0.0 /10 ×2 0.0 /10 ×2 0.0 /10 ×2 10.0 /10 ×2 0.0 /10 ×2

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 97 v3.26.0 70 v3.26.0 96 v3.26.0 基准（参考） 98 v3.26.0

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 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 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 11131 ms 12827 ms 9890 ms 10447 ms 17288 ms

输出速度 105.8 tok/s 13.1 tok/s 156.8 tok/s 126.4 tok/s 137.4 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 ⓘ

$0.0567

$0.1193

$0.0665

$0.0620

$0.0894

缓存读取占比 ⓘ 82% 23% 82% 83% 82%

揭晓

通道

服务商 LinkAPI ↗

通道O-Max

服务商 WorldBase.ai ↗

通道M-

服务商 LingxiCode ↗

通道M-

官方基准

服务商 OmniaKey ↗

通道O-Max

返回列表