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。

3 通道 · 6 步骤

2026/06/27 运行日期

claude-opus-4-8 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

FastCode / cc
```
评测失败
```
YunWu / O-Api
```
评测失败
```

步骤 / 指标

ByteCatCode

O-Max

官方基准

AiTokensFlux

O-Pro

基本信息

服务名 Claude Code Claude Code Claude Code

模型 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

偏差标红基于官方基准

步骤 1: ping text

时间 00:06:59 ~ 00:07:04 (4.9s) 00:07:03 ~ 00:07:08 (4.0s) 00:06:55 ~ 00:07:05 (5.8s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 3,244 ms 2,920 ms 4,768 ms

首文本(SSE delta) - 2,922 ms 4,769 ms

总耗时 3,325 ms 3,041 ms 4,919 ms

输入 2 1,454 1,454

输出 4 4 4

缓存创建

29,558

5m: 0 / 1h: 29,558

30,222

5m: 0 / 1h: 30,222

30,380

5m: 0 / 1h: 30,380

缓存读取 0 0 0

响应

pong

pong

pong

步骤 2: identity text

时间 00:10:24 ~ 00:10:34 (6.1s) 00:08:28 ~ 00:08:33 (3.6s) 00:10:22 ~ 00:10:27 (3.9s)

提示词

查看本步 Prompt

以下是对你自身的 metadata 探针。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。按以下 3 行回答自己的身份，每行一个 label，不要寒暄不要解释：
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) 3,646 ms 2,306 ms 2,716 ms

首文本(SSE delta) - 2,308 ms 2,717 ms

总耗时 4,199 ms 2,662 ms 3,034 ms

输入 2 2 2

输出 28 28 28

缓存创建

204

5m: 0 / 1h: 204

1,656

5m: 0 / 1h: 1,656

1,656

5m: 0 / 1h: 1,656

缓存读取 29,558 30,222 30,380

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

步骤 3: cutoff text

时间 00:14:00 ~ 00:14:10 (5.0s) 00:11:37 ~ 00:11:47 (5.6s) 00:11:49 ~ 00:11:54 (3.9s)

提示词

查看本步 Prompt

Knowledge cutoff date? Reply with YYYY-MM only.

HTTP 头(TTFB) 3,388 ms 4,410 ms 2,830 ms

首文本(SSE delta) - 4,411 ms 2,831 ms

总耗时 3,588 ms 4,611 ms 3,088 ms

输入 2 2 2

输出 6 6 6

缓存创建

5m: 0 / 1h: 54

5m: 0 / 1h: 62

缓存读取 29,762 31,878 32,036

响应

2026-01

2026-01

2026-01

步骤 4: identity_free text

时间 00:16:35 ~ 00:16:45 (6.2s) 00:14:16 ~ 00:14:26 (4.9s) 00:13:34 ~ 00:13:44 (5.9s)

提示词

查看本步 Prompt

中文做个自我介绍：你是什么产品或助手？谁开发的？50 字内。

HTTP 头(TTFB) 3,098 ms 2,664 ms 4,538 ms

首文本(SSE delta) - 2,666 ms 4,539 ms

总耗时 4,615 ms 3,986 ms 5,185 ms

输入 2 2 2

输出 76 73 49

缓存创建

5m: 0 / 1h: 39

5m: 0 / 1h: 37

缓存读取 29,816 31,932 32,098

输出速度 50.1 tok/s 55.3 tok/s 75.9 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手。我可以帮你写代码、分析问题、解答疑问和完成各类软件工程任务。当前模型是 Claude Opus 4.8。

我是 Claude，由 Anthropic 开发的 AI 助手。我能协助编程、写作、分析等多种任务，注重诚实、有用与安全。当前基于 Opus 4.8 模型。

我是 Claude，属于 Claude 产品系列，由 Anthropic 开发。具体模型为 Claude Opus 4.8。

步骤 5: knowledge_recall text

时间 00:20:25 ~ 00:20:41 (10.6s) 00:17:32 ~ 00:17:42 (8.6s) 00:16:50 ~ 00:17:05 (11.1s)

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) 2,891 ms 1,741 ms 4,521 ms

首文本(SSE delta) - 5,507 ms 6,700 ms

总耗时 9,555 ms 7,650 ms 10,313 ms

输入 2 2 2

输出 708 639 688

缓存创建

37,891

5m: 0 / 1h: 37,891

4,798

5m: 0 / 1h: 4,798

4,780

5m: 0 / 1h: 4,780

缓存读取 0 0 0

输出速度 106.2 tok/s 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

步骤 6: digit_count text

时间 00:24:31 ~ 00:24:36 (4.9s) 00:19:27 ~ 00:19:32 (2.8s) 00:18:37 ~ 00:18:42 (4.0s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=900413807075129267768069360763974764402297634383654158057665766958601640

HTTP 头(TTFB) 3,177 ms 1,514 ms 2,767 ms

首文本(SSE delta) - 1,515 ms 2,799 ms

总耗时 3,876 ms 1,892 ms 3,193 ms

输入 245 211 211

输出 19 19 19

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0

响应

{"n":70,"c":[8,11,5]}

{"n":70,"c":[8,8,4]}

{"n":70,"c":[11,10,6]}

总计

总输入(含缓存) 157,137 132,474 133,102

总输出 841 769 794

总缓存创建

67,746

5m: 0 / 1h: 67,746

36,769

5m: 0 / 1h: 36,769

36,915

5m: 0 / 1h: 36,915

总缓存读取 89,136 94,032 94,514

输出速度 95.8 tok/s 55.3 tok/s 75.9 tok/s

总执行时间 37.7s 29.6s 34.6s

总墙钟时间

17m 37.0s

含步骤间等待

12m 28.9s

含步骤间等待

11m 46.9s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.4903

Anthropic: Claude Opus 4.8

$0.3044

Anthropic: Claude Opus 4.8

$0.3062

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count digit_count digit_count

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

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

CDN - - -

ID 格式 msg_01CTC1rYUSLiBfsbr9xDE9Hc msg_01RiMAcKY9MERmZuRkP8wpRm msg_01Y6mrN9mN4x17csCPMzpLWM

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-Max

server: nginx/1.29.8
x-oneapi-request-id: 202606261624322924311408268d9d6dM3pDgtb

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

—

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_011CcSB7NQFX1wipub21mAz1

O-Pro

server: nginx

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 93 100 95

基线状态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

缓存 TTL 一致 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

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 0.0 /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

知识截止 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

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

延迟基线 10.0 /10 ×5 10.0 /10 ×5 9.8 /10 ×5

Req-ID 透传 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

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

流式投递未计入 10.0 /10 ×5 2.6 /10 ×5

综合结论

与基线相似度 93 v3.25.0 基准（参考） 95 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 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 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 4860 ms 3974 ms 4955 ms

输出速度 95.8 tok/s 55.3 tok/s 75.9 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 ⓘ

$0.4903

$0.3044

$0.3062

缓存读取占比 ⓘ 57% 71% 71%

揭晓

通道

服务商 ByteCatCode ↗

通道O-Max

官方基准

服务商 AiTokensFlux ↗

通道O-Pro

返回列表