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

2026/06/22 运行日期

claude-opus-4-8 官方基准

1 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

DawAPI / cc
```
评测失败
```

步骤 / 指标

官方基准

FoxCode

ClaudeCN

O-Max

AIMZ

M-Max

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 13:04:00 ~ 13:04:05 (3.9s) 13:03:52 ~ 13:04:02 (5.0s) 13:03:58 ~ 13:04:08 (4.9s) 13:03:54 ~ 13:04:04 (5.1s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,295 ms 3,447 ms 3,406 ms 3,006 ms

首文本(SSE delta) 2,298 ms 3,449 ms 3,407 ms 3,051 ms

总耗时 2,657 ms 3,636 ms 3,571 ms 3,394 ms

输入 1,454 1,454 1,454 1,428

输出 4 4 4 4

缓存创建

30,222

5m: 0 / 1h: 30,222

30,222

5m: 30,222 / 1h: 0

30,224

5m: 0 / 1h: 30,224

29,758

5m: 0 / 1h: 29,758

缓存读取 0 0 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 13:06:15 ~ 13:06:20 (4.0s) 13:06:56 ~ 13:07:01 (4.3s) 13:06:09 ~ 13:06:19 (5.2s) 13:05:13 ~ 13:05:18 (4.2s)

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) 2,690 ms 2,905 ms 3,128 ms 2,651 ms

首文本(SSE delta) 2,692 ms 2,911 ms 3,129 ms 3,090 ms

总耗时 2,965 ms 3,352 ms 3,772 ms 3,090 ms

输入 2 2 2 2

输出 28 28 28 28

缓存创建

1,643

5m: 0 / 1h: 1,643

1,643

5m: 1,643 / 1h: 0

1,643

5m: 0 / 1h: 1,643

1,617

5m: 0 / 1h: 1,617

缓存读取 30,222 30,222 30,224 29,758

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-4-5

步骤 3: cutoff text

时间 13:09:13 ~ 13:09:18 (4.2s) 13:10:54 ~ 13:10:59 (4.4s) 13:09:11 ~ 13:09:21 (8.3s) 13:07:35 ~ 13:07:40 (4.4s)

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) 2,442 ms 3,279 ms 5,725 ms 2,703 ms

首文本(SSE delta) 2,443 ms 3,280 ms 5,726 ms 2,851 ms

总耗时 2,736 ms 3,572 ms 5,978 ms 2,937 ms

输入 2 2 2 2

输出 6 6 6 6

缓存创建

5m: 0 / 1h: 64

5m: 64 / 1h: 0

5m: 0 / 1h: 62

5m: 0 / 1h: 64

缓存读取 31,865 31,865 31,867 31,375

响应

2026-01

2026-01

2025-01

2025-03

步骤 4: identity_free text

时间 13:10:57 ~ 13:11:02 (4.3s) 13:12:50 ~ 13:12:55 (4.3s) 13:12:34 ~ 13:12:44 (5.9s) 13:11:10 ~ 13:11:20 (5.5s)

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) 1,687 ms 2,752 ms 3,356 ms 2,903 ms

首文本(SSE delta) 1,689 ms 2,753 ms 3,357 ms 3,564 ms

总耗时 3,120 ms 3,482 ms 4,529 ms 4,371 ms

输入 2 2 2 2

输出 70 44 68 47

缓存创建

5m: 0 / 1h: 35

5m: 39 / 1h: 0

5m: 0 / 1h: 31

5m: 0 / 1h: 39

缓存读取 31,929 31,929 31,929 31,439

输出速度 48.9 tok/s 60.4 tok/s 58.0 tok/s 58.2 tok/s

响应

我是 Claude，由 Anthropic 打造的 AI 助手，当前模型为 Claude Opus 4.8，可通过命令行、桌面应用等多种方式协助软件工程任务。

我是 Claude，由 Anthropic 开发的人工智能助手，能协助编程、写作、分析等多种任务。

我是 Claude，一个由 Anthropic 开发的人工智能助手。我基于 Claude Opus 4.8 模型，可以帮你处理编程、写作、分析等各类任务。

我是 Claude，由 Anthropic 开发的 AI 助手，可帮助完成软件工程、问答、写作等任务。

步骤 5: knowledge_recall text

时间 13:13:48 ~ 13:13:58 (8.7s) 13:16:04 ~ 13:16:14 (8.5s) 13:14:10 ~ 13:14:20 (8.8s) 13:12:25 ~ 13:12:35 (5.3s)

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) 2,366 ms 2,238 ms 3,058 ms 1,485 ms

首文本(SSE delta) 5,515 ms 5,072 ms 5,363 ms 4,110 ms

总耗时 7,699 ms 7,544 ms 7,710 ms 4,206 ms

输入 2 2 2 2

输出 701 692 595 317

缓存创建

4,788

5m: 0 / 1h: 4,788

4,766

5m: 4,766 / 1h: 0

4,782

5m: 0 / 1h: 4,782

4,279

5m: 0 / 1h: 4,279

缓存读取 0 0 0 0

输出速度 burst 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 13:17:42 ~ 13:17:48 (3.1s) 13:18:43 ~ 13:18:48 (3.1s) 13:15:41 ~ 13:15:46 (4.3s) 13:14:16 ~ 13:14:21 (2.9s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=478923735300103524728264059714928720042123696861995273962503420259125490

HTTP 头(TTFB) 1,619 ms 1,864 ms 2,442 ms 1,332 ms

首文本(SSE delta) 1,937 ms 1,865 ms 2,443 ms 1,333 ms

总耗时 2,097 ms 2,241 ms 3,315 ms 1,722 ms

输入 211 211 211 140

输出 19 19 19 19

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0

响应

{"n":70,"c":[6,5,7]}

{"n":70,"c":[6,5,6]}

{"n":70,"c":[5,7,9]}

{"n":72,"c":[6,7,9]}

总计

总输入(含缓存) 132,441 132,423 132,435 129,905

总输出 828 793 720 421

总缓存创建

36,752

5m: 0 / 1h: 36,752

36,734

5m: 36,734 / 1h: 0

36,742

5m: 0 / 1h: 36,742

35,757

5m: 0 / 1h: 35,757

总缓存读取 94,016 94,016 94,020 92,572

输出速度 48.9 tok/s 60.4 tok/s 58.0 tok/s 58.2 tok/s

总执行时间 28.1s 29.5s 37.5s 27.4s

总墙钟时间

13m 48.0s

含步骤间等待

14m 56.9s

含步骤间等待

11m 48.0s

含步骤间等待

10m 28.0s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.3058

Anthropic: Claude Opus 4.8

$0.2187

Anthropic: Claude Opus 4.8

$0.3030

Anthropic: Claude Opus 4.8

$0.2882

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count digit_count digit_count digit_count

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

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

CDN - cloudflare cloudflare cloudflare

ID 格式 msg_01UvUaqMc3K7dNGmrAsupe4X msg_01Gdw3LhSJjJ1mGNsUs8kgph msg_01DT2F5Q29jkyEqNNpNravzt msg_0167cemgsH3H6qw4aPEZuL2H

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
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_011CcHjQwiPL8P8oLBgxDcFF
cc	cf-ray: a0f8cb49f8eee393-NRT server: cloudflare set-cookie: _cfuvid=gRWSnOB6y3rzzgTrq2ZDchuYGkemJCMJg5Ut89WF_Ao-1782105525.235163-1.0.1.1-MiGxBn8tgqwRSSz7XuCukua9umflKV3aGqSEOO4Fw.g; 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_011CcHjVSvue5HYKzA7HF3a2 a0f8cb49f8eee393-NRT
O-Max	cf-ray: a0f8c6d41a8b50ff-AMS server: cloudflare x-oneapi-request-id: 20260622131542639484164kFGjPkGw	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	a0f8c6d41a8b50ff-AMS
M-Max	cf-ray: a0f8c4c76b21d5a5-AMS server: cloudflare x-new-api-version: v0.0.0 x-oneapi-request-id: 202606220514181921136068268d9d6eVINaQHS	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-idhdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a0f8c4c76b21d5a5-AMS

协议指纹评分（机器自动）

总分 / 100 100 92 91 79

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 10.0 /10 ×20 10.0 /10 ×20

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

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

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

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

身份(结构) 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 0.0 /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

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 10.0 /10 ×5 10.0 /10 ×5

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

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

与基线相似度基准（参考） 92 v3.24.0 91 v3.24.0 79 v3.24.0

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 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 3546 ms 3971 ms 4813 ms 3287 ms

输出速度 48.9 tok/s 60.4 tok/s 58.0 tok/s 58.2 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 ⓘ

$0.3058

$0.2187

$0.3030

$0.2882

缓存读取占比 ⓘ 71% 71% 71% 71%

揭晓

通道

官方基准

服务商 FoxCode ↗

通道cc

服务商 ClaudeCN ↗

通道O-Max

服务商 AIMZ ↗

通道M-Max

返回列表