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

2026/06/22 运行日期

claude-sonnet-4-6 官方基准

1 任务失败执行不完整

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

官方基准

ByteCatCode

O-Max

FastCode

SAIAi

O-Max

基本信息

服务名 Claude Code Claude Code Claude Code Claude Code

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

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 04:37:09 ~ 04:37:14 (4.4s) 04:37:01 ~ 04:37:06 (4.6s) 04:37:05 ~ 04:37:15 (5.5s) 04:37:07 ~ 04:37:12 (4.6s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 3,027 ms 3,292 ms 3,906 ms 3,442 ms

首文本(SSE delta) 3,030 ms - 3,908 ms 3,444 ms

总耗时 3,114 ms 3,414 ms 3,995 ms 3,579 ms

输入 3 3 3 3

输出 5 5 5 5

缓存创建

32,318

5m: 0 / 1h: 32,318

32,346

5m: 32,346 / 1h: 0

32,318

5m: 0 / 1h: 32,318

32,318

5m: 0 / 1h: 32,318

缓存读取 0 0 0 0

响应

pong

pong

pong

pong

步骤 2: identity text

时间 04:41:00 ~ 04:41:10 (5.3s) 04:38:40 ~ 04:38:45 (4.5s) 04:40:12 ~ 04:40:22 (7.6s) 04:38:17 ~ 04:38:22 (3.6s)

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) 3,820 ms 2,964 ms 5,297 ms 2,215 ms

首文本(SSE delta) 3,822 ms - 5,302 ms 2,217 ms

总耗时 4,392 ms 3,442 ms 6,338 ms 2,566 ms

输入 3 3 3 3

输出 22 22 22 22

缓存创建

178

5m: 0 / 1h: 178

178

5m: 178 / 1h: 0

178

5m: 0 / 1h: 178

178

5m: 0 / 1h: 178

缓存读取 32,318 32,346 32,318 32,318

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

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

步骤 3: cutoff text

时间 04:43:42 ~ 04:43:48 (3.1s) 04:40:01 ~ 04:40:06 (4.7s) 04:43:23 ~ 04:43:28 (4.8s) 04:40:43 ~ 04:40:49 (3.6s)

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) 1,952 ms 3,108 ms 3,548 ms 2,395 ms

首文本(SSE delta) 2,061 ms - 3,549 ms 2,397 ms

总耗时 2,129 ms 3,326 ms 3,611 ms 2,583 ms

输入 3 3 3 3

输出 8 8 8 8

缓存创建

5m: 0 / 1h: 55

5m: 38 / 1h: 0

5m: 0 / 1h: 38

5m: 0 / 1h: 57

缓存读取 32,496 32,524 32,496 32,496

响应

2025-08

2025-08

2025-08

2025-08

步骤 4: identity_free text

时间 04:45:30 ~ 04:45:35 (4.5s) 04:44:06 ~ 04:44:16 (5.6s) 04:44:52 ~ 04:45:02 (7.5s) 04:43:25 ~ 04:43:35 (5.0s)

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) 2,865 ms 3,389 ms 4,970 ms 2,874 ms

首文本(SSE delta) 3,269 ms - 4,980 ms 2,876 ms

总耗时 3,525 ms 4,275 ms 6,313 ms 3,756 ms

输入 3 3 3 3

输出 51 55 49 59

缓存创建

5m: 0 / 1h: 41

5m: 35 / 1h: 0

5m: 0 / 1h: 43

缓存读取 32,551 32,562 32,534 32,553

输出速度 - 62.1 tok/s 36.8 tok/s 67.0 tok/s

响应

我叫 Claude，是由 Anthropic 开发的 AI 助手，属于 Claude 产品系列。当前版本为 claude-sonnet-4-6。

我是 Claude，由 Anthropic 开发的 AI 助手。我基于大型语言模型构建，旨在提供安全、有益的对话和任务协助。

我是 Claude，由 Anthropic 开发的 AI 助手。我能帮助你完成写作、分析、编程、问答等多种任务。

我是 Claude，由 Anthropic 开发的 AI 助手，基于大型语言模型构建，能够帮助完成写作、分析、编程、问答等多种任务。

步骤 5: knowledge_recall text

时间 04:48:24 ~ 04:48:29 (4.9s) 04:47:28 ~ 04:47:33 (4.8s) 04:46:05 ~ 04:46:15 (5.4s) 04:45:51 ~ 04:46:01 (5.0s)

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) 1,603 ms 1,783 ms 1,921 ms 2,168 ms

首文本(SSE delta) 1,604 ms - 1,923 ms 2,170 ms

总耗时 3,542 ms 3,640 ms 4,286 ms 4,098 ms

输入 3 3 3 3

输出 205 205 204 205

缓存创建

8,032

5m: 0 / 1h: 8,032

8,041

5m: 8,041 / 1h: 0

8,015

5m: 0 / 1h: 8,015

8,044

5m: 0 / 1h: 8,044

缓存读取 0 0 0 0

输出速度 105.8 tok/s 110.4 tok/s 86.3 tok/s 106.3 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 04:51:05 ~ 04:51:25 (17.2s) 04:48:37 ~ 04:48:57 (16.3s) 04:48:18 ~ 04:48:38 (15.8s) 04:48:50 ~ 04:49:10 (18.3s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=875072816291921518634477725899589218069516821897003224046252033671287509

HTTP 头(TTFB) 3,172 ms 1,774 ms 4,232 ms 1,521 ms

首文本(SSE delta) 3,174 ms - 4,233 ms 1,522 ms

总耗时 16,238 ms 15,000 ms 14,688 ms 17,102 ms

输入 164 193 164 164

输出 1,227 1,347 806 1,384

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0

输出速度 93.9 tok/s 101.8 tok/s 77.1 tok/s 88.8 tok/s

响应

```
s = 875072816291921518634477725899589218069516821897003224046252033671287509
```

**Counting length (groups of 10):**
```
8750728162  → 10
9192151863  → 10
4477725899  → 10
5892180695  → 10
168218

## Counting digits in `s = 875072816291921518634477725899589218069516821897003224046252033671287509`

**Step 1 — Length (split into groups of 10):**
```
8750728162 | 9192151863 | 4477725899 | 58921806

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

**Verification walkthrough**

String: `875072816291921518634477725899589218069516821897003224046252033671287509`

| digit | positions (1-based) | count |
|-------|---

## Counting digits in:
`875072816291921518634477725899589218069516821897003224046252033671287509`

### Length
Splitting into groups of 10:
```
8750728162  (10)
9192151863  (10)
4477725899  (10)
589218

总计

总输入(含缓存) 138,168 138,278 138,119 138,186

总输出 1,518 1,642 1,094 1,683

总缓存创建

40,624

5m: 0 / 1h: 40,624

40,638

5m: 40,638 / 1h: 0

40,592

5m: 0 / 1h: 40,592

40,640

5m: 0 / 1h: 40,640

总缓存读取 97,365 97,432 97,348 97,367

输出速度 95.5 tok/s 100.6 tok/s 74.8 tok/s 89.6 tok/s

总执行时间 39.4s 40.5s 46.6s 40.0s

总墙钟时间

14m 16.0s

含步骤间等待

11m 56.0s

含步骤间等待

11m 33.1s

含步骤间等待

12m 2.9s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.2049

Anthropic: Claude Sonnet 4.6

$0.1497

Anthropic: Claude Sonnet 4.6

$0.1984

Anthropic: Claude Sonnet 4.6

$0.2074

Anthropic: Claude Sonnet 4.6

通道指纹

来源步骤 digit_count digit_count digit_count digit_count

平台 direct (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 - - - -

ID 格式 msg_01B1UUijRsNjtLhPYCZS5SMN msg_01ByfRwUehQLbTCVtKWjPCNa msg_01BVir8cspnGH4oGTBbmthgD msg_01QB5zV1QZh8KTpbceDZ58VW

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
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_011CcH4nDhMkSnoKTgjj8UP9
O-Max	server: nginx/1.29.8 x-oneapi-request-id: 202606212048389538198778268d9d6hkB6ZxA1	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	—
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	—
O-Max	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_011CcH4cGaDYnrJhL2D1jmeN

协议指纹评分（机器自动）

总分 / 100 100 89 98 100

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 10.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20

缓存 TTL 一致 10.0 /10 ×15 0.0 /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 10.0 /10 ×13 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 10.0 /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 10.0 /10 ×6

inference_geo 10.0 /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 10.0 /10 ×5 未计入 10.0 /10 ×5 10.0 /10 ×5

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

综合结论

与基线相似度基准（参考） 89 v3.24.0 98 v3.24.0 100 v3.24.0

雷达图例

共 21 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 流式投递 buffer_dump_match
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 中文遵循 instruction_following_lang
20 档位思考量 tier_thinking_volume_match
21 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 5490 ms 5516 ms 6539 ms 5614 ms

输出速度 95.5 tok/s 100.6 tok/s 74.8 tok/s 89.6 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 ⓘ

$0.2049

$0.1497

$0.1984

$0.2074

缓存读取占比 ⓘ 70% 70% 70% 70%

揭晓

通道

官方基准

服务商 ByteCatCode ↗

通道O-Max

服务商 FastCode ↗

通道cc

服务商 SAIAi ↗

通道O-Max

返回列表