模型对比 | RPDiag

测试说明点击展开 5 步 quick-probe-v1 详解

同一会话连续 5 步，覆盖 5 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。步与步之间随机延迟 1–4 分钟。第 3 步（cutoff）累计跨度 > 5 分钟保住 sliding cache 检测；全流程总跨度 > 6 分钟容纳新增的第 5 步。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。

2 通道 · 5 步骤

2026/06/16 运行日期

claude-opus-4-8 官方基准

3 任务失败执行不完整

已揭晓揭晓进度

⚠ 3 通道不可测 · 已从主对比表移除点击展开原因

InfAI / R-Kiro
```
评测失败
```
DawAPI / cc
```
评测失败
```
DBAI / M-
```
评测失败
```

步骤 / 指标

ClaudeAPI

O-Bdrk

官方基准

基本信息

服务名 Claude Code Claude Code

模型 claude-opus-4-8 claude-opus-4-8

客户端 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 15:47:17 ~ 15:47:27 (8.5s) 15:47:22 ~ 15:47:27 (4.6s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 4,581 ms 3,367 ms

首文本(SSE delta) 4,584 ms 3,369 ms

总耗时 5,087 ms 3,483 ms

输入 1,454 1,454

输出 4 4

缓存创建

30,222

5m: 30,222 / 1h: 0

30,222

5m: 0 / 1h: 30,222

缓存读取 0 0

响应

pong

pong

步骤 2: identity text

时间 15:50:14 ~ 15:50:24 (6.9s) 15:49:01 ~ 15:49:06 (3.8s)

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。请只输出以下 3 行内容（label 小写，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) 3,713 ms 2,364 ms

首文本(SSE delta) 4,240 ms 2,366 ms

总耗时 4,240 ms 2,771 ms

输入 2 2

输出 28 28

缓存创建

1,630

5m: 1,630 / 1h: 0

1,630

5m: 0 / 1h: 1,630

缓存读取 30,222 30,222

响应

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 15:53:11 ~ 15:53:21 (6.2s) 15:50:44 ~ 15:50:54 (6.6s)

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) 4,228 ms 5,107 ms

首文本(SSE delta) 4,229 ms 5,150 ms

总耗时 4,637 ms 5,592 ms

输入 2 2

输出 6 6

缓存创建

5m: 62 / 1h: 0

5m: 0 / 1h: 62

缓存读取 31,852 31,852

响应

2026-01

2026-01

步骤 4: identity_free text

时间 15:55:22 ~ 15:55:32 (7.6s) 15:53:09 ~ 15:53:14 (4.2s)

提示词

查看本步 Prompt

用中文回答：你是谁？由谁开发？50 字以内。

HTTP 头(TTFB) 4,252 ms 2,500 ms

首文本(SSE delta) 4,255 ms 2,502 ms

总耗时 5,683 ms 3,138 ms

输入 2 2

输出 65 44

缓存创建

5m: 31 / 1h: 0

5m: 0 / 1h: 35

缓存读取 31,914 31,914

输出速度 45.5 tok/s 69.2 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手。当前模型是 Claude Opus 4.8，可以帮你处理编程、写作、分析等各类任务。

我是 Claude，由 Anthropic 打造的 AI 助手，当前模型为 Claude Opus 4.8。

步骤 5: knowledge_recall text

时间 15:59:09 ~ 15:59:24 (11.0s) 15:56:29 ~ 15:56:54 (22.2s)

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) 2,883 ms 10,301 ms

首文本(SSE delta) 6,715 ms 18,758 ms

总耗时 9,243 ms 21,170 ms

输入 2 2

输出 721 672

缓存创建

4,766

5m: 0 / 1h: 4,766

4,747

5m: 0 / 1h: 4,747

缓存读取 0 0

输出速度 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

总计

总输入(含缓存) 132,161 132,146

总输出 824 754

总缓存创建

36,711

5m: 31,945 / 1h: 4,766

36,696

5m: 0 / 1h: 36,696

总缓存读取 93,988 93,988

输出速度 45.5 tok/s 69.2 tok/s

总执行时间 40.3s 41.3s

总墙钟时间

12m 7.8s

含步骤间等待

9m 31.8s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.2295

Anthropic: Claude Opus 4.8

$0.3025

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 knowledge_recall knowledge_recall

平台 one-api (100%) direct (100%)

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

CDN - -

ID 格式 msg_013o7wTrRUL1rSYCxSYtuVWF msg_01VR5Xj81yNmFKivJ8fjGgav

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

O-Bdrk

x-new-api-version: v2026.05.18
x-oneapi-request-id: 202606160759117064632298268d9d6GfZsxAhY

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

—

协议指纹评分（机器自动）

总分 / 100 88 100

基线状态已对照基线已对照基线

缓存命中比 10.0 /10 ×20 10.0 /10 ×20

缓存 TTL 一致 0.0 /10 ×15 10.0 /10 ×15

模型匹配 10.0 /10 ×14 10.0 /10 ×14

缓存连续性 10.0 /10 ×14 10.0 /10 ×14

sliding 5m 10.0 /10 ×13 10.0 /10 ×13

原生 msg-ID 10.0 /10 ×8 10.0 /10 ×8

系统提示纯净 10.0 /10 ×8 10.0 /10 ×8

身份(结构) 10.0 /10 ×7 10.0 /10 ×7

知识截止 10.0 /10 ×7 10.0 /10 ×7

身份(自由) 10.0 /10 ×7 10.0 /10 ×7

service_tier 10.0 /10 ×6 10.0 /10 ×6

inference_geo 10.0 /10 ×5 10.0 /10 ×5

延迟基线 10.0 /10 ×5 10.0 /10 ×5

Req-ID 透传 0.0 /10 ×4 10.0 /10 ×4

stop_reason 10.0 /10 ×3 10.0 /10 ×3

SDK 一致 10.0 /10 ×2 10.0 /10 ×2

流式投递 — —

综合结论

与基线相似度 88 v3.18.0 基准（参考）

雷达图例

共 19 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 自由身份 identity_free_clean
6 停止原因 stop_reason_present
7 系统提示纯净 system_prompt_clean
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 中文遵循 instruction_following_lang
19 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 5778 ms 7231 ms

输出速度 45.5 tok/s 69.2 tok/s

完成步骤 5/5 成功 5/5 成功

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.2295

$0.3025

缓存读取占比 ⓘ 71% 71%

揭晓

通道

服务商 ClaudeAPI ↗

通道O-Bdrk

官方基准

返回列表