模型对比 | RPDiag

测试说明点击展开 5 步 quick-probe-v1 详解

前 4 步同一会话（交互 TUI 多轮），第 5、6 步各自独立新会话，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 1-3 步的延迟在交互进程内发生，让缓存前缀在墙钟里老化）。第 3 步（cutoff）累计跨度 > 5 分钟保住 sliding cache 检测；总跨度 > 6 分钟。第 5 步（知识召回）与第 6 步（档位）都是独立新会话（第 6 步不复用上下文，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

2026/07/02 运行日期

claude-sonnet-4-6 官方基准

2 任务失败执行不完整

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

InfAI / R-Kiro

不可测：未取得可评分响应（如 403 / 上游错误）

TopRouterCN / O-Max

不可测：未取得可评分响应（如 403 / 上游错误）

步骤 / 指标

ClaudeAPI

O-Bdrk

sucui

O-Max

官方基准

基本信息

服务名 Claude Code Claude Code Claude Code

模型 claude-sonnet-4-6 claude-sonnet-4-6 claude-sonnet-4-6

客户端 claude-cli v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195

偏差标红基于官方基准

步骤 1: ping text

时间 23:39:10 ~ 23:45:26 (372.8s) 23:39:12 ~ 23:49:13 (599.2s) 23:39:14 ~ 23:45:20 (364.8s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 5,223 ms 2,575 ms 3,413 ms

首文本(SSE delta) 5,466 ms 2,586 ms 3,414 ms

总耗时 5,466 ms 2,681 ms 3,551 ms

输入 3 3 3

输出 5 5 5

缓存创建

22,263

5m: 0 / 1h: 22,263

6,217

5m: 0 / 1h: 6,217

6,217

5m: 0 / 1h: 6,217

缓存读取 0 16,046 16,046

响应

pong

pong

pong

步骤 2: identity text

时间 23:39:10 ~ 23:45:26 (372.8s) 23:39:12 ~ 23:49:13 (599.2s) 23:39:14 ~ 23:45:20 (364.8s)

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。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) 4,948 ms 2,283 ms 3,036 ms

首文本(SSE delta) 4,949 ms 2,284 ms 3,037 ms

总耗时 5,677 ms 3,697 ms 3,378 ms

输入 3 3 3

输出 22 22 22

缓存创建

191

5m: 0 / 1h: 191

191

5m: 0 / 1h: 191

191

5m: 0 / 1h: 191

缓存读取 22,263 22,263 22,263

响应

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

步骤 3: cutoff text

时间 23:39:10 ~ 23:45:26 (372.8s) 23:39:12 ~ 23:49:13 (599.2s) 23:39:14 ~ 23:45:20 (364.8s)

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) 3,088 ms 2,020 ms 3,315 ms

首文本(SSE delta) 3,090 ms 2,154 ms 3,316 ms

总耗时 3,291 ms 2,261 ms 3,456 ms

输入 3 3 3

输出 8 8 8

缓存创建

6,465

5m: 0 / 1h: 6,465

5m: 0 / 1h: 38

缓存读取 16,046 22,454 22,454

响应

2025-08

2025-08

2025-08

步骤 4: identity_free text

时间 23:39:10 ~ 23:45:26 (372.8s) 23:39:12 ~ 23:49:13 (599.2s) 23:39:14 ~ 23:45:20 (364.8s)

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) 4,003 ms 3,331 ms 5,332 ms

首文本(SSE delta) 4,004 ms 3,332 ms 5,344 ms

总耗时 4,789 ms 4,943 ms 6,262 ms

输入 3 3 3

输出 51 72 44

缓存创建

5m: 0 / 1h: 41

5m: 0 / 1h: 35

5m: 0 / 1h: 39

缓存读取 22,511 22,492 22,492

输出速度 65.0 tok/s 44.7 tok/s 47.9 tok/s

响应

æå« Claudeï¼æ¯ç± Anthropic å¼åç AI å©æï¼å±äº Claude ç³»åäº§åãå½åçæ¬ä¸º Claude Sonnet 4.6ã

ææ¯

ææ¯ Claudeï¼ç± Anthropic æé ç AI å©æãå½åè¿è¡çæ¨¡åçæ¬ä¸º claude-sonnet-4-6ã

步骤 5: knowledge_recall text

时间 23:54:35 ~ 23:54:55 (18.0s) 23:56:08 ~ 23:56:28 (17.7s) 23:54:05 ~ 23:58:30 (18.0s)

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) 2,381 ms 1,755 ms 1,491 ms

首文本(SSE delta) 2,382 ms 1,757 ms 1,492 ms

总耗时 4,821 ms 3,349 ms 3,396 ms

输入 3 3 3

输出 204 205 205

缓存创建

4,660

5m: 0 / 1h: 4,660

4,660

5m: 0 / 1h: 4,660

4,660

5m: 0 / 1h: 4,660

缓存读取 2,129 2,129 2,129

输出速度 83.6 tok/s 128.8 tok/s 107.7 tok/s

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 23:57:55 ~ 23:58:20 (23.4s) 23:58:09 ~ 23:58:34 (22.2s) 23:59:58 ~ 07/03 00:00:23 (21.3s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=669913775245508629417186972097712855246354235480939390338082103296287107

HTTP 头(TTFB) 5,112 ms 5,592 ms 1,021 ms

首文本(SSE delta) 5,113 ms 5,612 ms 1,022 ms

总耗时 21,475 ms 20,742 ms 20,126 ms

输入 164 164 164

输出 1,390 1,437 2,020

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0

输出速度 85.0 tok/s 95.0 tok/s 105.7 tok/s

响应

## Counting digits in `s = 669913775245508629417186972097712855246354235480939390338082103296287107`

### Step 1 — Total length

Breaking into groups of 10:
```
6699137752 | 4550862941 | 7186972097 |

## Counting digits in s

**s** = `669913775245508629417186972097712855246354235480939390338082103296287107`

### Length
Splitting into groups of 10:
```
6699137752 | 4550862941 | 7186972097 | 71285524

## Counting digits in `s`

**String:** `669913775245508629417186972097712855246354235480939390338082103296287107`

### Step 1 – Total length

Breaking into groups of 10:
```
6699137752 | 4550862941 |

总计

总输入(含缓存) 96,748 96,704 96,708

总输出 1,680 1,749 2,304

总缓存创建

33,620

5m: 0 / 1h: 33,620

11,141

5m: 0 / 1h: 11,141

11,145

5m: 0 / 1h: 11,145

总缓存读取 62,949 85,384 85,384

输出速度 84.0 tok/s 93.5 tok/s 103.5 tok/s

总执行时间 25m 32.6s 40m 36.6s 24m 58.4s

总墙钟时间

19m 10.6s

含步骤间等待

19m 22.1s

含步骤间等待

21m 9.4s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.1707

Anthropic: Claude Sonnet 4.6

$0.0942

Anthropic: Claude Sonnet 4.6

$0.1025

Anthropic: Claude Sonnet 4.6

通道指纹

来源步骤 digit_count digit_count digit_count

平台 one-api (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_016Dwpb5CTscpasDtRLRSQZH msg_01B9dKZHJMUdjQL5VevRPVQU msg_019amDe8e4otuwCjePZdWx8Z

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: v1.0.0-rc.11
x-oneapi-request-id: 202607021557577905621198268d9d6i8KNDUkQ

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

—

O-Max

via: 1.1 Caddy
cf-ray: a14ed9b59f9337cb-FRA
server: cloudflare
x-new-api-version: v0.12.10
x-oneapi-request-id: 202607021558108946449588268d9d6Si7fJgvd

id_format: msg_prefix
via_chain: ["1.1 Caddy"]
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-rayhdr:viabody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body

a14ed9b59f9337cb-FRA

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_011CcdWUkwfEaXBrmMtsX3p7

协议指纹评分（机器自动）

总分 / 100 95 99 100

基线状态已对照基线已对照基线已对照基线

缓存命中比 7.7 /10 ×20 10.0 /10 ×20 10.0 /10 ×20

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

延迟基线 9.9 /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

缓存连续性 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

原生 msg-ID 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

身份(结构) 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

知识截止 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

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

stop_reason 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3

Req-ID 透传 0.0 /10 ×2 0.0 /10 ×2 10.0 /10 ×2

SDK 一致 10.0 /10 ×2 10.0 /10 ×2 10.0 /10 ×2

流式投递未计入未计入未计入

综合结论

与基线相似度 95 v3.27.0 99 v3.27.0 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 自由身份 identity_free_clean
5 停止原因 stop_reason_present
6 系统提示纯净 system_prompt_clean
7 Service Tier service_tier_present
8 缓存命中比 cache_hit_ratio_match
9 缓存 TTL 一致 cache_ttl_consistency
10 推理地区 inference_geo_present
11 缓存连续 cache_continuity_intra
12 知识召回 knowledge_recall_match
13 延迟基线 latency_baseline_match
14 原生 msg-ID anthropic_msg_id_format
15 Sliding 缓存 cache_sliding_correctness
16 结构化身份 identity_structured_match
17 信封自报一致 envelope_self_report_match
18 档位思考量 tier_thinking_volume_match
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 7587 ms 6279 ms 6695 ms

输出速度 84.0 tok/s 93.5 tok/s 103.5 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 ⓘ

$0.1707

$0.0942

$0.1025

缓存读取占比 ⓘ 65% 88% 88%

揭晓

通道

服务商 ClaudeAPI ↗

通道O-Bdrk

服务商 sucui ↗

通道O-Max

官方基准

返回列表