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

2026/06/28 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

DBAI / M-
```
评测失败
```

步骤 / 指标

SSSAiCode

R-Kiro

LinkAPI

O-Max

官方基准

ClaudeAPI

O-Bdrk

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 07:01:52 ~ 07:01:57 (3.7s) 07:01:48 ~ 07:01:53 (3.4s) 07:01:54 ~ 07:01:59 (4.0s) 07:01:46 ~ 07:01:56 (5.1s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,844 ms 1,340 ms 2,910 ms 2,021 ms

首文本(SSE delta) 2,877 ms 1,342 ms 2,911 ms 2,031 ms

总耗时 2,879 ms 2,341 ms 3,065 ms 3,545 ms

输入 0 1,454 1,454 1,454

输出 4 4 4 4

缓存创建

30,222

5m: 30,222 / 1h: 0

30,222

5m: 0 / 1h: 30,222

30,222

5m: 30,222 / 1h: 0

缓存读取 0 0 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 07:03:05 ~ 07:03:10 (3.1s) 07:03:20 ~ 07:03:25 (4.2s) 07:05:12 ~ 07:05:27 (10.6s) 07:03:22 ~ 07:03:32 (5.0s)

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) 2,134 ms 1,616 ms 9,249 ms 1,776 ms

首文本(SSE delta) 2,139 ms 1,618 ms 9,256 ms 1,777 ms

总耗时 2,281 ms 3,054 ms 9,554 ms 3,420 ms

输入 0 2 2 2

输出 28 28 28 28

缓存创建

1,643

5m: 1,643 / 1h: 0

1,643

5m: 0 / 1h: 1,643

1,643

5m: 1,643 / 1h: 0

缓存读取 0 30,222 30,222 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-4-8

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

步骤 3: cutoff text

时间 07:05:32 ~ 07:05:37 (3.3s) 07:05:56 ~ 07:06:06 (5.4s) 07:09:11 ~ 07:09:16 (3.9s) 07:05:19 ~ 07:05:24 (4.0s)

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) 2,339 ms 3,317 ms 2,828 ms 1,779 ms

首文本(SSE delta) 2,372 ms 3,318 ms 2,830 ms 1,780 ms

总耗时 2,483 ms 4,435 ms 2,998 ms 2,654 ms

输入 0 2 2 2

输出 8 6 6 6

缓存创建

5m: 54 / 1h: 0

5m: 0 / 1h: 54

5m: 64 / 1h: 0

缓存读取 0 31,865 31,865 31,865

响应

2026-01

2026-01

2026-01

2026-01

步骤 4: identity_free text

时间 07:07:37 ~ 07:07:42 (3.6s) 07:07:45 ~ 07:07:50 (4.3s) 07:12:53 ~ 07:12:58 (3.9s) 07:06:43 ~ 07:06:53 (8.0s)

提示词

查看本步 Prompt

中文回答：你叫什么、属于哪个产品、谁开发？50 字内。

HTTP 头(TTFB) 2,679 ms 1,261 ms 1,970 ms 5,752 ms

首文本(SSE delta) 2,759 ms 1,262 ms 1,972 ms 5,754 ms

总耗时 2,905 ms 3,100 ms 2,947 ms 6,701 ms

输入 0 2 2 31,970

输出 38 68 57 61

缓存创建

5m: 31 / 1h: 0

5m: 0 / 1h: 31

5m: 0 / 1h: 0

缓存读取 0 31,919 31,919 0

输出速度 - 37.0 tok/s 58.5 tok/s 64.4 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手，当前模型为 Claude Opus 4.8。

我是 Claude，由 Anthropic 公司开发的人工智能助手。当前模型是 Claude Opus 4.8，可以帮助你处理编程、写作、问答等各类任务。

我是 Claude，由 Anthropic 开发的人工智能助手，当前模型为 Claude Opus 4.8，可协助处理编程及各类任务。

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

步骤 5: knowledge_recall text

时间 07:09:59 ~ 07:10:09 (8.3s) 07:09:31 ~ 07:09:46 (13.7s) 07:15:48 ~ 07:15:58 (9.2s) 07:10:01 ~ 07:10:16 (11.6s)

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) 5,255 ms 6,043 ms 1,966 ms 4,400 ms

首文本(SSE delta) 6,458 ms 9,345 ms 5,774 ms 7,783 ms

总耗时 7,485 ms 12,722 ms 8,233 ms 10,253 ms

输入 0 2 2 4,785

输出 335 682 701 680

缓存创建

4,772

5m: 4,772 / 1h: 0

4,761

5m: 0 / 1h: 4,761

5m: 0 / 1h: 0

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 07:12:01 ~ 07:12:12 (8.8s) 07:12:09 ~ 07:12:14 (3.4s) 07:18:07 ~ 07:18:12 (2.7s) 07:12:51 ~ 07:12:56 (4.8s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=754323908979385936026285122859441131796281168429630475860964274519338102

HTTP 头(TTFB) 5,209 ms 805 ms 1,365 ms 2,189 ms

首文本(SSE delta) 8,080 ms 808 ms 1,367 ms 2,190 ms

总耗时 8,084 ms 2,341 ms 1,729 ms 3,556 ms

输入 0 211 211 211

输出 20 19 19 19

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0

响应

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

{"n":72,"c":[5,4,9]}

{"n":72,"c":[3,5,8]}

{"n":72,"c":[5,7,9]}

总计

总输入(含缓存) 0 132,401 132,390 132,440

总输出 433 807 815 798

总缓存创建

36,722

5m: 36,722 / 1h: 0

36,711

5m: 0 / 1h: 36,711

31,929

5m: 31,929 / 1h: 0

总缓存读取 0 94,006 94,006 62,087

输出速度 burst 37.0 tok/s 58.5 tok/s 64.4 tok/s

总执行时间 30.8s 34.3s 34.4s 38.4s

总墙钟时间

10m 19.9s

含步骤间等待

10m 26.9s

含步骤间等待

16m 18.4s

含步骤间等待

11m 10.1s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

>=$0.0108

Anthropic: Claude Opus 4.8 (成本不完整)

$0.2190

Anthropic: Claude Opus 4.8

$0.3052

Anthropic: Claude Opus 4.8

$0.3678

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

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

CDN - - - -

ID 格式 msg_89fc1af4bd764241852e9d6f5b1cc209 msg_018eVrNRYjyhRj7MEnMrVJUb msg_012U5opynpXKEbSm6rTp5V6v msg_013hvuRbsYDuy4xhhqkABE9c

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
R-Kiro	server: Photon-Edge x-amzn-requestid: 383e116c-cb54-47b2-88fc-d54684305935	id_format: msg_prefix has_service_tier: false has_inference_geo: false model_has_date_suffix: false usage_has_cache_fields: true	body:id:msg_prefixbody:usage.cache_fieldsupstream:x-amzn-requestidupstream:anthropic-direct-from-body	1782601922952-zsxv68seqo6go 383e116c-cb54-47b2-88fc-d54684305935
O-Max	server: nginx set-cookie: server_name_session=7d88fca8b1426ca76c58d5aeba6fb224; Max-Age=86400; httponly; path=/ x-new-api-version: v1.0.0-rc.15 x-oneapi-request-id: 202606272312109777161178268d9d6oJYOjMNF	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_011CcUcr1ZEtpjRbLVwLpEvH
O-Bdrk	x-new-api-version: v1.0.0-rc.11 x-oneapi-request-id: 202606272312523712467098268d9d6lFgLHmiK	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	—

协议指纹评分（机器自动）

总分 / 100 52 89 100 82

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 0.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20 5.3 /10 ×20

缓存 TTL 一致 0.0 /10 ×15 0.0 /10 ×15 10.0 /10 ×15 0.0 /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 5.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14

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

原生 msg-ID 0.0 /10 ×8 10.0 /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

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

流式投递 4.1 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

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

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

综合结论

与基线相似度 52 v3.25.0 89 v3.25.0 基准（参考） 82 v3.25.0

雷达图例

共 20 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 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 缓存连续 cache_continuity_intra
13 知识召回 knowledge_recall_match
14 延迟基线 latency_baseline_match
15 原生 msg-ID anthropic_msg_id_format
16 Sliding 缓存 cache_sliding_correctness
17 结构化身份 identity_structured_match
18 信封自报一致 envelope_self_report_match
19 档位思考量 tier_thinking_volume_match
20 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 4353 ms 4666 ms 4754 ms 5022 ms

输出速度 burst 37.0 tok/s 58.5 tok/s 64.4 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 ⓘ

>=$0.0108 (成本不完整)

$0.2190

$0.3052

$0.3678

缓存读取占比 ⓘ - 71% 71% 47%

揭晓

通道

服务商 SSSAiCode ↗

通道R-Kiro

服务商 LinkAPI ↗

通道O-Max

官方基准

服务商 ClaudeAPI ↗

通道O-Bdrk

返回列表