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

2026/06/23 运行日期

claude-opus-4-8 官方基准

1 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

TopRouterCN / O-Max
```
评测失败
```

步骤 / 指标

duckcoding

cc专用

ClaudeCN

O-Max

官方基准

FastCode

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 18:17:33 ~ 18:17:43 (5.1s) 18:17:37 ~ 18:17:47 (5.1s) 18:17:39 ~ 18:17:44 (3.7s) 18:17:35 ~ 18:17:40 (4.8s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 3,815 ms 3,223 ms 2,464 ms 2,669 ms

首文本(SSE delta) 3,830 ms 3,225 ms 2,465 ms 2,670 ms

总耗时 4,064 ms 3,415 ms 2,636 ms 2,813 ms

输入 1,454 1,454 1,454 1,454

输出 4 4 4 4

缓存创建

30,223

5m: 0 / 1h: 30,223

30,225

5m: 0 / 1h: 30,225

30,222

5m: 0 / 1h: 30,222

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 18:20:45 ~ 18:20:55 (7.0s) 18:20:33 ~ 18:20:43 (5.0s) 18:19:52 ~ 18:19:57 (4.7s) 18:19:55 ~ 18:20:05 (5.5s)

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。自报身份，输出严格遵守以下 3 行格式（不允许 markdown、代码块、额外文本）：
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) 4,356 ms 3,176 ms 3,368 ms 3,653 ms

首文本(SSE delta) 4,890 ms 3,177 ms 3,370 ms 3,660 ms

总耗时 5,877 ms 3,622 ms 3,652 ms 4,090 ms

输入 2 2 2 2

输出 28 28 28 28

缓存创建

1,646

5m: 0 / 1h: 1,646

1,646

5m: 0 / 1h: 1,646

1,646

5m: 0 / 1h: 1,646

31,868

5m: 0 / 1h: 31,868

缓存读取 30,223 30,225 30,222 0

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 18:22:42 ~ 18:22:52 (6.3s) 18:24:18 ~ 18:24:28 (5.9s) 18:23:51 ~ 18:23:56 (3.4s) 18:22:28 ~ 18:22:33 (3.8s)

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) 4,343 ms 3,146 ms 2,222 ms 2,259 ms

首文本(SSE delta) 4,693 ms 3,147 ms 2,223 ms 2,261 ms

总耗时 5,498 ms 3,446 ms 2,450 ms 2,597 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

1,700

5m: 0 / 1h: 1,700

缓存读取 31,869 31,871 31,868 30,222

响应

2026-01

2026-01

2026-01

2026-01

步骤 4: identity_free text

时间 18:26:45 ~ 18:26:55 (9.6s) 18:26:25 ~ 18:26:35 (5.5s) 18:27:16 ~ 18:27:21 (4.9s) 18:26:31 ~ 18:27:36 (61.9s)

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) 7,809 ms 3,431 ms 2,578 ms 2,543 ms

首文本(SSE delta) 8,040 ms 3,432 ms 2,579 ms 2,545 ms

总耗时 8,643 ms 4,450 ms 3,616 ms 5,027 ms

输入 2 2 2 2

输出 45 65 70 -

缓存创建

31,968

5m: 0 / 1h: 31,968

5m: 0 / 1h: 39

5m: 0 / 1h: 31

31,961

5m: 0 / 1h: 31,961

缓存读取 0 31,925 31,922 0

输出速度 74.6 tok/s 63.9 tok/s 67.5 tok/s -

响应

我是 Claude，由 Anthropic 开发，属于 Claude 模型系列（当前为 Opus 4.8）。

我是 Claude，由 Anthropic 开发的 AI 助手，基于 Claude Opus 4.8 模型，可帮助你完成编程、写作、分析等各类任务。

我是 Claude，由 Anthropic 公司开发的人工智能助手。我当前的模型是 Claude Opus 4.8，可以帮助你处理编程、写作、分析等各种任务。

我是 Claude，由 Anthropic 开发的 AI 助手。我可以帮助处理软件工程、写作、分析等多种任务，致力于提供有用、准确且安全的协助。

步骤 5: knowledge_recall text

时间 18:29:45 ~ 18:30:15 (28.3s) 18:29:14 ~ 18:29:34 (18.0s) 18:29:17 ~ 18:29:27 (9.6s) 18:30:49 ~ 18:31:09 (16.8s)

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) 16,059 ms 10,400 ms 2,711 ms 5,971 ms

首文本(SSE delta) 16,944 ms 14,630 ms 6,000 ms 8,469 ms

总耗时 27,288 ms 16,889 ms 8,384 ms 15,356 ms

输入 2 2 2 2

输出 715 768 709 659

缓存创建

4,767

5m: 0 / 1h: 4,767

4,783

5m: 0 / 1h: 4,783

4,777

5m: 0 / 1h: 4,777

4,783

5m: 0 / 1h: 4,783

缓存读取 0 0 0 0

输出速度 69.1 tok/s burst burst 95.7 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

{"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 18:34:07 ~ 18:34:12 (4.0s) 18:33:26 ~ 18:33:31 (4.1s) 18:31:25 ~ 18:31:30 (2.7s) 18:32:48 ~ 18:32:58 (5.7s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=226871205088603794870204534407996874602761292120479350654326256241216857

HTTP 头(TTFB) 2,205 ms 2,244 ms 1,379 ms 3,328 ms

首文本(SSE delta) 2,415 ms 2,245 ms 1,380 ms 3,649 ms

总耗时 3,262 ms 2,894 ms 1,773 ms 4,444 ms

输入 212 211 211 211

输出 19 19 19 19

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0

响应

{"n":72,"c":[7,8,5]}

{"n":72,"c":[7,7,4]}

{"n":72,"c":[8,9,5]}

{"n":72,"c":[7,7,4]}

总计

总输入(含缓存) 132,432 132,441 132,415 132,429

总输出 817 890 836 716

总缓存创建

68,666

5m: 0 / 1h: 68,666

36,747

5m: 0 / 1h: 36,747

36,730

5m: 0 / 1h: 36,730

100,534

5m: 0 / 1h: 100,534

总缓存读取 62,092 94,021 94,012 30,222

输出速度 69.4 tok/s 63.9 tok/s 67.5 tok/s 95.7 tok/s

总执行时间 1m 0.4s 43.6s 29.0s 1m 38.4s

总墙钟时间

16m 39.1s

含步骤间等待

15m 54.0s

含步骤间等待

13m 51.0s

含步骤间等待

15m 23.1s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.4890

Anthropic: Claude Opus 4.8

$0.3073

Anthropic: Claude Opus 4.8

$0.3058

Anthropic: Claude Opus 4.8

$0.6697

Anthropic: Claude Opus 4.8

通道指纹

来源步骤 digit_count digit_count digit_count digit_count

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

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

CDN - cloudflare - -

ID 格式 msg_01KFaH54i5pcQRsh1UdvEuv2 msg_019cFFtLFexZXz1FSpN7G5ub msg_01VZuKjfmZRkfd9SzMMGq7Jr msg_01FwPDk4vXECWkoPRnWaNhiM

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
cc专用	server: Nginx x-oneapi-request-id: 202606231034086407545698268d9d6mxonw01X	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	—
O-Max	cf-ray: a102d5ac987f167e-AMS server: cloudflare x-oneapi-request-id: 202606231833283211046004BadQpPZ	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	a102d5ac987f167e-AMS
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_011CcL39MACBe1WsDpfSf5dD
cc	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 91 98 100 72

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 5.3 /10 ×20 10.0 /10 ×20 10.0 /10 ×20 0.0 /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 7.7 /10 ×13 10.0 /10 ×13 10.0 /10 ×13 5.3 /10 ×13

原生 msg-ID 10.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8 0.0 /10 ×8

系统提示纯净 10.0 /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 10.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6 0.0 /10 ×6

inference_geo 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 0.0 /10 ×5

延迟基线 9.4 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

流式投递 10.0 /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 7.0 /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 91 v3.24.0 98 v3.24.0 基准（参考） 72 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 9105 ms 5786 ms 3752 ms 5721 ms

输出速度 69.4 tok/s 63.9 tok/s 67.5 tok/s 95.7 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 ⓘ

$0.4890

$0.3073

$0.3058

$0.6697

缓存读取占比 ⓘ 47% 71% 71% 23%

揭晓

通道

服务商 duckcoding ↗

通道cc专用

服务商 ClaudeCN ↗

通道O-Max

官方基准

服务商 FastCode ↗

通道cc

返回列表