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

2026/06/24 运行日期

claude-opus-4-8 官方基准

2 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

LingxiCode / M-
```
评测失败
```
Aiberm / cc
```
评测失败
```

步骤 / 指标

WorldBase.ai

M-

HongMaCC

u-cc

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 15:59:30 ~ 15:59:45 (13.6s) 15:59:32 ~ 15:59:42 (4.9s) 15:59:38 ~ 15:59:48 (5.8s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 11,811 ms 3,313 ms 4,407 ms

首文本(SSE delta) 11,989 ms 3,314 ms 4,409 ms

总耗时 12,012 ms 3,315 ms 4,595 ms

输入 1,042 0 1,454

输出 2 22 4

缓存创建

21,772

5m: 0 / 1h: 21,772

5m: 0 / 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 16:01:27 ~ 16:01:37 (8.0s) 16:03:02 ~ 16:03:07 (3.5s) 16:01:39 ~ 16:01:44 (4.0s)

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。请按下列 3 行格式精确填空作答（label 不变，值小写）：
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) 6,309 ms 2,329 ms 2,646 ms

首文本(SSE delta) 6,421 ms 2,331 ms 2,648 ms

总耗时 6,626 ms 2,331 ms 3,049 ms

输入 225 0 2

输出 15 107 28

缓存创建

22,815

5m: 0 / 1h: 22,815

5m: 0 / 1h: 0

1,634

5m: 0 / 1h: 1,634

缓存读取 0 0 30,222

输出速度 - 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

步骤 3: cutoff text

时间 16:03:44 ~ 16:03:54 (9.4s) 16:07:07 ~ 16:07:12 (3.7s) 16:03:19 ~ 16:03:29 (6.7s)

提示词

查看本步 Prompt

请直接回答你的知识截止日期，格式 YYYY-MM，不要附加任何说明。

HTTP 头(TTFB) 6,102 ms 2,542 ms 5,208 ms

首文本(SSE delta) 6,104 ms 2,543 ms 5,240 ms

总耗时 6,316 ms 2,544 ms 5,622 ms

输入 46 0 2

输出 3 34 6

缓存创建

245

5m: 0 / 1h: 245

5m: 0 / 1h: 0

5m: 0 / 1h: 54

缓存读取 22,815 0 31,856

输出速度 - burst -

响应

2026-01

2026-01

2026-01

步骤 4: identity_free text

时间 16:06:06 ~ 16:06:16 (8.3s) 16:08:30 ~ 16:08:35 (3.3s) 16:06:41 ~ 16:06:51 (9.4s)

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) 6,594 ms 2,177 ms 7,020 ms

首文本(SSE delta) 6,595 ms 2,178 ms 7,058 ms

总耗时 7,000 ms 2,178 ms 8,277 ms

输入 46 0 2

输出 38 35 61

缓存创建

1,336

5m: 0 / 1h: 1,336

5m: 0 / 1h: 0

5m: 0 / 1h: 31

缓存读取 21,772 0 31,910

输出速度 93.8 tok/s burst 50.0 tok/s

响应

我是 Claude Code，Anthropic 开发的命令行 AI 编程助手，基于 Claude 模型，帮你完成编码和软件工程任务。

我是 Claude，由 Anthropic 开发的 AI 助手。

我是 Claude，由 Anthropic 开发的人工智能助手。当前模型为 Claude Opus 4.8，可协助编程、写作、分析等多种任务。

步骤 5: knowledge_recall text

时间 16:08:36 ~ 16:08:51 (13.1s) 16:11:52 ~ 16:12:22 (25.1s) 16:10:29 ~ 16:10:39 (8.8s)

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) 9,556 ms 23,502 ms 2,530 ms

首文本(SSE delta) 9,994 ms 23,503 ms 5,423 ms

总耗时 11,741 ms 24,009 ms 7,795 ms

输入 753 0 2

输出 168 5,526 673

缓存创建

114

5m: 0 / 1h: 114

5m: 0 / 1h: 0

4,756

5m: 0 / 1h: 4,756

缓存读取 2,791 0 0

输出速度 96.2 tok/s 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

步骤 6: digit_count text

时间 16:11:19 ~ 16:11:39 (18.8s) 16:14:16 ~ 16:14:26 (5.6s) 16:13:09 ~ 16:13:14 (3.1s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=306356252284238956625052989333191280076744297198714184559554835707265850

HTTP 头(TTFB) 2,753 ms 4,385 ms 1,648 ms

首文本(SSE delta) 2,755 ms 4,386 ms 1,650 ms

总耗时 16,803 ms 4,507 ms 2,107 ms

输入 33 0 211

输出 1,547 684 19

缓存创建

175

5m: 175 / 1h: 0

5m: 0 / 1h: 0

缓存读取 0 0 0

输出速度 110.1 tok/s burst -

响应

```
s = "306356252284238956625052989333191280076744297198714184559554835707265850"
```

Going through each character:

- Length: 72
- 0s at positions 2,22,36,37,65,72 → **6**
- 7s at positions 38,40,4

{"n":78,"c":[6,5,7]}

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

总计

总输入(含缓存) 95,980 0 132,358

总输出 1,773 6,408 791

总缓存创建

46,457

5m: 175 / 1h: 46,282

5m: 0 / 1h: 0

36,697

5m: 0 / 1h: 36,697

总缓存读取 47,378 0 93,988

输出速度 108.2 tok/s burst 50.0 tok/s

总执行时间 1m 11.2s 46.2s 37.7s

总墙钟时间

12m 9.0s

含步骤间等待

14m 54.1s

含步骤间等待

13m 35.9s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.3687

Anthropic: Claude Opus 4.8

>=$0.1602

Anthropic: Claude Opus 4.8 (成本不完整)

$0.3045

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count digit_count digit_count

平台 direct (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_01n2FgYuHnP0TaruqPQvQIxc msg_71fad25bcc06e4d40b944195 msg_01HMYnpahh1MaBmHnzp4F6wc

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: a10a42e2cedbdf30-AMS
server: cloudflare

id_format: msg_prefix
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_fieldsupstream:anthropic-direct-from-body

6d970b92-2d56-4941-92bf-45292bdb0caf
a10a42e2cedbdf30-AMS

u-cc

server: nginx
x-new-api-version: 1.0.15
x-oneapi-request-id: 202606240814175992137618268d9d6QVyGNxPR

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_011CcMkQieDPN3PPuYEU6vQe

协议指纹评分（机器自动）

总分 / 100 75 55 100

基线状态已对照基线已对照基线已对照基线

缓存命中比 6.5 /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 5.0 /10 ×14 10.0 /10 ×14

sliding 5m 7.7 /10 ×13 5.0 /10 ×13 10.0 /10 ×13

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

系统提示纯净 0.0 /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

知识截止 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

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 5.6 /10 ×5 10.0 /10 ×5 9.5 /10 ×5

流式投递 10.0 /10 ×5 0.0 /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 75 v3.24.0 55 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 10083 ms 6481 ms 5241 ms

输出速度 108.2 tok/s burst 50.0 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 ⓘ

$0.3687

>=$0.1602 (成本不完整)

$0.3045

缓存读取占比 ⓘ 49% - 71%

揭晓

通道

服务商 WorldBase.ai ↗

通道M-

服务商 HongMaCC ↗

通道u-cc

官方基准

返回列表