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

2026/06/27 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

TopRouterCN / O-Max
```
评测失败
```

步骤 / 指标

WorldBase.ai

M-

LingxiCode

M-

HongMaCC

u-cc

官方基准

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 04:08:42 ~ 04:08:58 (11.9s) 04:08:37 ~ 04:08:42 (4.4s) 04:08:40 ~ 04:08:46 (3.1s) 04:08:44 ~ 04:08:55 (5.2s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 9,539 ms 3,387 ms 2,019 ms 4,073 ms

首文本(SSE delta) 9,540 ms 3,394 ms 2,020 ms 4,075 ms

总耗时 10,436 ms 3,729 ms 2,020 ms 4,160 ms

输入 1 1,454 0 1,454

输出 54 4 25 4

缓存创建

2,445

30,225

5m: 0 / 1h: 30,225

5m: 0 / 1h: 0

30,222

5m: 0 / 1h: 30,222

缓存读取 22,581 0 0 0

输出速度 60.3 tok/s - - -

响应

I'm ready. What would you like to work on?

pong

pong

pong

步骤 2: identity text

时间 04:11:04 ~ 04:11:19 (14.2s) 04:09:45 ~ 04:09:55 (5.9s) 04:11:13 ~ 04:11:18 (3.3s) 04:10:45 ~ 04:10:55 (5.7s)

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) 6,337 ms 4,104 ms 2,196 ms 4,490 ms

首文本(SSE delta) 6,755 ms 4,105 ms 2,197 ms 4,492 ms

总耗时 13,156 ms 4,800 ms 2,197 ms 4,694 ms

输入 1 2 0 2

输出 113 28 135 28

缓存创建

2,197

1,656

5m: 0 / 1h: 1,656

5m: 0 / 1h: 0

1,656

5m: 0 / 1h: 1,656

缓存读取 22,219 30,225 0 30,222

输出速度 17.7 tok/s - burst -

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 04:12:20 ~ 04:12:35 (11.2s) 04:13:46 ~ 04:13:51 (4.9s) 04:15:15 ~ 04:15:20 (3.2s) 04:12:29 ~ 04:12:39 (5.6s)

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) 9,991 ms 3,540 ms 2,042 ms 4,480 ms

首文本(SSE delta) 10,137 ms 3,541 ms 2,043 ms 4,482 ms

总耗时 10,173 ms 4,060 ms 2,043 ms 4,655 ms

输入 1 2 0 2

输出 25 6 39 6

缓存创建

2,450

5m: 0 / 1h: 54

5m: 0 / 1h: 0

5m: 0 / 1h: 64

缓存读取 24,766 31,881 0 31,878

输出速度 - - burst -

响应

2026-01

2026-01

2026-01

2026-01

步骤 4: identity_free text

时间 04:16:12 ~ 04:16:27 (14.1s) 04:15:57 ~ 04:16:07 (6.5s) 04:19:12 ~ 04:19:17 (3.7s) 04:15:38 ~ 04:15:48 (6.1s)

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) 10,972 ms 3,758 ms 2,614 ms 4,251 ms

首文本(SSE delta) 10,973 ms 3,760 ms 2,615 ms 4,253 ms

总耗时 12,977 ms 5,102 ms 2,615 ms 5,187 ms

输入 1 2 0 2

输出 98 67 49 61

缓存创建

3,155

5m: 0 / 1h: 39

5m: 0 / 1h: 0

5m: 0 / 1h: 35

缓存读取 31,840 31,935 0 31,942

输出速度 48.9 tok/s 49.9 tok/s burst 65.3 tok/s

响应

我是 Claude，由 Anthropic 打造的 AI 助手，当前作为编程助手运行，模型为 claude-opus-4-8。

我是 Claude，由 Anthropic 开发的 AI 助手。我可以帮你写代码、分析问题、查找资料和处理各类软件工程任务。很高兴为你服务！

我是Claude，属于Claude产品，由Anthropic开发。

我是 Claude，由 Anthropic 打造的 AI 助手。当前模型为 Claude Opus 4.8，可用于编程、研究、写作等多种任务。

步骤 5: knowledge_recall text

时间 04:19:56 ~ 04:20:11 (13.3s) 04:18:56 ~ 04:19:06 (9.7s) 04:22:48 ~ 04:23:03 (13.9s) 04:19:01 ~ 04:19:16 (10.8s)

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) 5,417 ms 2,685 ms 12,268 ms 3,632 ms

首文本(SSE delta) 5,791 ms 6,539 ms 12,269 ms 5,068 ms

总耗时 12,277 ms 9,015 ms 12,560 ms 9,831 ms

输入 1 2 0 2

输出 411 678 1,864 689

缓存创建

544

4,795

5m: 0 / 1h: 4,795

5m: 0 / 1h: 0

4,792

5m: 0 / 1h: 4,792

缓存读取 5,195 0 0 0

输出速度 63.4 tok/s burst burst 144.7 tok/s

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 04:23:03 ~ 04:23:09 (3.9s) 04:22:46 ~ 04:22:51 (4.6s) 04:25:26 ~ 04:25:36 (8.3s) 04:21:19 ~ 04:21:29 (4.5s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=724749026308982479564995061959227434288286872778291016247304897712988052

HTTP 头(TTFB) 2,609 ms 2,896 ms 6,902 ms 3,297 ms

首文本(SSE delta) 2,675 ms 2,903 ms 6,903 ms 3,299 ms

总耗时 2,859 ms 3,875 ms 7,074 ms 3,636 ms

输入 1 211 0 211

输出 25 19 1,040 19

缓存创建

5m: 0 / 1h: 0

缓存读取 216 0 0 0

输出速度 - - burst -

响应

{"n":72,"c":[3,9,9]}

{"n":72,"c":[5,9,11]}

{"n":72,"c":[6,10,10]}

{"n":72,"c":[3,9,12]}

总计

总输入(含缓存) 117,684 132,483 0 132,484

总输出 726 802 3,152 807

总缓存创建

10,861

36,769

5m: 0 / 1h: 36,769

5m: 0 / 1h: 0

36,769

5m: 0 / 1h: 36,769

总缓存读取 106,817 94,041 0 94,042

输出速度 42.8 tok/s 49.9 tok/s burst 131.6 tok/s

总执行时间 1m 8.6s 36.0s 35.5s 37.9s

总墙钟时间

14m 26.0s

含步骤间等待

14m 14.9s

含步骤间等待

16m 55.2s

含步骤间等待

12m 44.7s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.1140

Anthropic: Claude Opus 4.8

$0.3052

Anthropic: Claude Opus 4.8

>=$0.0788

Anthropic: Claude Opus 4.8 (成本不完整)

$0.3054

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count digit_count digit_count digit_count

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

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

CDN cloudflare cloudflare - -

ID 格式 msg_C85SQSP8QJlexjGB9o9G70 msg_01SkS5s4zxorZaR5u7ENuBs9 msg_b0cebe8ad8471e7d331861d8 msg_01VMpuznKxcnprVQbF1zGDP7

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
M-	cf-ray: a11eed813aece247-AMS server: cloudflare	id_format: msg_prefix has_service_tier: false has_inference_geo: false model_has_date_suffix: false usage_has_cache_fields: true	hdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.cache_fieldsupstream:anthropic-direct-from-body	b92e3be6-e854-49ab-9843-632be5e5f77c a11eed813aece247-AMS
M-	cf-ray: a11eed137f58e041-NRT server: cloudflare set-cookie: server_name_session=27f4a95581d368605416e6d0825f8e16; Max-Age=86400; httponly; path=/ x-oneapi-request-id: 20260626202248285712735chXIVt5O	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-idhdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a11eed137f58e041-NRT
u-cc	server: nginx x-new-api-version: 1.0.17 x-oneapi-request-id: 202606262025273715519578268d9d6jZ2WZQCm	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	—
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_011CcSVZUkpBuTQeMCsWBEWy

协议指纹评分（机器自动）

总分 / 100 70 98 53 100

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 0.0 /10 ×20 10.0 /10 ×20

缓存 TTL 一致 0.0 /10 ×15 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 10.0 /10 ×14

缓存连续性 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 5.0 /10 ×13 10.0 /10 ×13

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

系统提示纯净 0.0 /10 ×8 10.0 /10 ×8 未计入 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 0.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6

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

延迟基线 4.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

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

Req-ID 透传 0.0 /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

综合结论

与基线相似度 70 v3.25.0 98 v3.25.0 53 v3.25.0 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 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 10313 ms 5097 ms 4752 ms 5361 ms

输出速度 42.8 tok/s 49.9 tok/s burst 131.6 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 ⓘ

$0.1140

$0.3052

>=$0.0788 (成本不完整)

$0.3054

缓存读取占比 ⓘ 91% 71% - 71%

揭晓

通道

服务商 WorldBase.ai ↗

通道M-

服务商 LingxiCode ↗

通道M-

服务商 HongMaCC ↗

通道u-cc

官方基准

返回列表