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

2026/06/19 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

AnyAIGC / M-
```
评测失败
```

步骤 / 指标

官方基准

ByteCatCode

O-Max

AIMZ

M-Max

LingxiCode

M-

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 07:24:24 ~ 07:24:30 (3.8s) 07:24:20 ~ 07:24:31 (6.9s) 07:24:22 ~ 07:24:28 (3.8s) 07:24:17 ~ 07:24:22 (4.8s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,469 ms 5,317 ms 2,442 ms 3,176 ms

首文本(SSE delta) 2,471 ms - 2,541 ms 3,177 ms

总耗时 2,612 ms 5,511 ms 2,627 ms 3,392 ms

输入 1,454 2 1,428 1,454

输出 4 4 4 4

缓存创建

30,222

5m: 0 / 1h: 30,222

36,466

5m: 0 / 1h: 36,466

29,758

5m: 0 / 1h: 29,758

30,222

5m: 0 / 1h: 30,222

缓存读取 0 0 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 07:27:14 ~ 07:27:19 (3.3s) 07:27:03 ~ 07:27:14 (6.7s) 07:26:57 ~ 07:27:02 (3.7s) 07:26:17 ~ 07:26:27 (5.2s)

提示词

查看本步 Prompt

输出 3 行 metadata 描述你自己（当前 API 模型）。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。禁止任何额外字符：
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) 1,887 ms 4,751 ms 2,319 ms 3,463 ms

首文本(SSE delta) 1,889 ms - 2,610 ms 3,782 ms

总耗时 2,189 ms 5,131 ms 2,699 ms 4,088 ms

输入 2 2 2 2

输出 28 28 30 28

缓存创建

1,643

5m: 0 / 1h: 1,643

191

5m: 0 / 1h: 191

1,617

5m: 0 / 1h: 1,617

1,643

5m: 0 / 1h: 1,643

缓存读取 30,222 36,466 29,758 30,222

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-4-20250514

vendor: anthropic
brand: claude
model: claude-opus-4-8

步骤 3: cutoff text

时间 07:29:35 ~ 07:29:55 (3.4s) 07:30:35 ~ 07:30:45 (5.2s) 07:28:40 ~ 07:28:45 (4.1s) 07:28:23 ~ 07:28:28 (4.3s)

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) 2,230 ms 3,889 ms 2,381 ms 3,309 ms

首文本(SSE delta) 2,232 ms - 2,634 ms 3,310 ms

总耗时 2,418 ms 4,108 ms 2,830 ms 3,544 ms

输入 2 2 2 2

输出 6 6 6 6

缓存创建

5m: 0 / 1h: 62

5m: 0 / 1h: 54

5m: 0 / 1h: 64

缓存读取 31,865 36,657 31,375 31,865

响应

2026-01

2026-01

2025-01

2026-01

步骤 4: identity_free text

时间 07:32:46 ~ 07:32:51 (3.8s) 07:34:14 ~ 07:34:24 (5.9s) 07:30:03 ~ 07:30:08 (4.3s) 07:29:29 ~ 07:29:39 (5.1s)

提示词

查看本步 Prompt

请用中文介绍你自己是什么产品或助手，由谁开发，50 字以内。

HTTP 头(TTFB) 1,963 ms 3,621 ms 2,426 ms 3,034 ms

首文本(SSE delta) 1,964 ms - 3,068 ms 3,036 ms

总耗时 2,773 ms 4,748 ms 3,181 ms 4,270 ms

输入 2 2 2 2

输出 61 68 61 66

缓存创建

5m: 0 / 1h: 39

5m: 0 / 1h: 31

5m: 0 / 1h: 39

缓存读取 31,927 36,711 31,439 31,929

输出速度 75.4 tok/s 60.3 tok/s - 53.5 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手，基于 Claude Opus 4.8 模型，可协助编程、写作、分析等多种任务。

我是 Claude，由 Anthropic 开发的 AI 助手。我可以帮助你编写代码、解答问题、处理文本等多种任务，致力于提供安全、有用的协助。

我是 Claude,一个由 Anthropic 开发的人工智能助手。我可以帮助你处理各种任务,比如回答问题、编写代码、分析内容等。

我是 Claude，由 Anthropic 开发的 AI 助手，能帮你编程、写作、分析问题和处理各类任务。当前模型为 Claude Opus 4.8。

步骤 5: knowledge_recall text

时间 07:34:30 ~ 07:34:40 (9.2s) 07:37:38 ~ 07:37:53 (11.1s) 07:31:20 ~ 07:31:30 (5.3s) 07:32:56 ~ 07:33:06 (9.2s)

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) 2,739 ms 4,831 ms 1,920 ms 2,640 ms

首文本(SSE delta) 5,994 ms - 1,921 ms 5,931 ms

总耗时 8,226 ms 10,076 ms 4,263 ms 8,442 ms

输入 2 2 2 2

输出 685 679 344 712

缓存创建

4,781

5m: 0 / 1h: 4,781

42,718

5m: 0 / 1h: 42,718

4,285

5m: 0 / 1h: 4,285

4,788

5m: 0 / 1h: 4,788

缓存读取 0 0 0 0

输出速度 burst 129.5 tok/s 146.9 tok/s 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 07:36:21 ~ 07:36:31 (7.2s) 07:40:54 ~ 07:41:09 (10.3s) 07:34:42 ~ 07:34:47 (3.7s) 07:35:29 ~ 07:35:34 (3.4s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=201788657056951157789197837910919944100303685763577317628753277240033364

HTTP 头(TTFB) 5,896 ms 3,782 ms 2,161 ms 1,905 ms

首文本(SSE delta) 5,898 ms - 2,162 ms 1,906 ms

总耗时 6,238 ms 9,229 ms 2,584 ms 2,451 ms

输入 211 2 140 211

输出 19 668 19 19

缓存创建

5m: 0 / 1h: 0

40,864

5m: 0 / 1h: 40,864

5m: 0 / 1h: 0

缓存读取 0 0 0 0

输出速度 - 122.6 tok/s - -

响应

{"n":72,"c":[8,12,7]}

{"n":72,"c":[8,13,7]}

{"n":72,"c":[8,12,7]}

{"n":70,"c":[6,15,8]}

总计

总输入(含缓存) 132,434 230,178 129,903 132,445

总输出 803 1,453 464 835

总缓存创建

36,747

5m: 0 / 1h: 36,747

120,332

5m: 0 / 1h: 120,332

35,755

5m: 0 / 1h: 35,755

36,756

5m: 0 / 1h: 36,756

总缓存读取 94,014 109,834 92,572 94,016

输出速度 75.4 tok/s 119.7 tok/s 146.9 tok/s 53.5 tok/s

总执行时间 30.6s 46.2s 24.8s 32.0s

总墙钟时间

12m 7.0s

含步骤间等待

16m 48.8s

含步骤间等待

10m 24.9s

含步骤间等待

11m 17.7s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.3051

Anthropic: Claude Opus 4.8

$0.8434

Anthropic: Claude Opus 4.8

$0.2892

Anthropic: Claude Opus 4.8

$0.3060

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%) one-api (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

ID 格式 msg_014kpnTye5nHehK7gR3ztoDU msg_01GVW8C63pyWsVmmr6B5hrAg msg_01UfRahBzrHUrMC1ZbMKaGG8 msg_01JLDi4V8t4iWjoeMZWcssqH

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_011CcBbxTDKz1Mxch8fyuXHf
O-Max	server: nginx/1.29.8 x-oneapi-request-id: 202606182340558354554288268d9d6fT7TdXZL	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-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
M-Max	cf-ray: a0de1b3d7a3549b9-AMS server: cloudflare x-new-api-version: v0.0.0 x-oneapi-request-id: 20260618233444878038368268d9d6aEPu2t4Q	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	a0de1b3d7a3549b9-AMS
M-	cf-ray: a0de1c601bc1734b-NRT server: cloudflare set-cookie: server_name_session=c970d3e192ef604080ca6feb75cd59ec; Max-Age=86400; httponly; path=/ x-oneapi-request-id: 202606182335312845217526GThou2L	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	a0de1c601bc1734b-NRT

协议指纹评分（机器自动）

总分 / 100 98 81 79 96

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 8.2 /10 ×20 3.6 /10 ×20 8.3 /10 ×20 8.2 /10 ×20

缓存 TTL 一致 10.0 /10 ×15 10.0 /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 0.0 /10 ×8 5.0 /10 ×8 10.0 /10 ×8

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

知识截止 10.0 /10 ×7 10.0 /10 ×7 0.0 /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 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 未计入 0.0 /10 ×5 10.0 /10 ×5

Req-ID 透传 10.0 /10 ×4 0.0 /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） 81 v3.24.0 79 v3.24.0 96 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 4076 ms 6467 ms 3031 ms 4365 ms

输出速度 75.4 tok/s 119.7 tok/s 146.9 tok/s 53.5 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 ⓘ

$0.3051

$0.8434

$0.2892

$0.3060

缓存读取占比 ⓘ 71% 48% 71% 71%

揭晓

通道

官方基准

服务商 ByteCatCode ↗

通道O-Max

服务商 AIMZ ↗

通道M-Max

服务商 LingxiCode ↗

通道M-

返回列表