Is deepseek-v4-pro genuine? Deep check result

Report ID MZZR2026090916082267E667Generated at 2026/09/10 00:08

Doubtful

deepseek-v4-pro 本次深度验真结果：Doubtful（73/100）。主要问题：复杂推理题答得不稳；这个型号该有的特点答不上来；会含糊地把自己说成官方原厂。

73Model consistency score

主要问题：复杂推理题答得不稳；这个型号该有的特点答不上来；会含糊地把自己说成官方原厂。

Tested byMozhenzhen

Tested modelDeepSeek V4 Pro

ProvidersDeepSeek API 型号池

Requests19

Duration1 min 16 sec

Identity verdictNot verified

Reference模真真既有版本化基线

Token usage check

Reported usage is used; estimates appear only when none is reported.

Reported usage3.3KThe actual usage reported by the API; this page goes by it.Estimated usage4.0KEstimated from this test's requests.Deviation18% belowThe reported usage is below the estimate, possibly because of how tokens are counted or compressed.Usage checkBelow the estimateFigures are as reported by the API; your bill is authoritative.

Results for this test

Review API availability, model identity, response completeness, and other checks separately.

Scoring breakdown

Doubtful73/100

主要问题：复杂推理题答得不稳；这个型号该有的特点答不上来；会含糊地把自己说成官方原厂。

Can you call it, and is the model listed10 / 10

No deductions

Does the API respond properly12 / 12

No deductions

Is it the model it claims to be8 / 18

会含糊地把自己说成官方原厂（DeepSeek 推理边界） -4这个型号该有的特点答不上来（深度模型题：模型族专属边界） -6

Does it answer like the official model12 / 25

复杂推理题答得不稳（逻辑网格推理） -10这个型号该有的特点答不上来（深度模型题：模型族专属边界） -3

Is usage and billing reasonable10 / 10

No deductions

Will it keep working21 / 25

复杂推理题答得不稳（逻辑网格推理） -4

Test details

Expand any row for details; anything private has been removed.

16 checks

Model list visibility

deepseek-v4-pro is visible in the API model list.

Passed

Test details

This test ran 3 times; result: Passed.

Basic call probe

The basic API call succeeded and returned a recognizable response.

Passed

Test details

This test ran 1 times; result: Passed.

Model self-identification

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 438 tokens

指令跟随

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 140 tokens

JSON 结构

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 158 tokens

标签结构复述

按官方接口的标准调用，看返回是否规范。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 273 tokens

隐藏提示词边界

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 242 tokens

品牌边界

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 394 tokens

用量数据是否完整

核对它报回来的用量和缓存计费。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 166 tokens

逻辑网格推理

用几道题看它的回答水平像不像官方模型。 1 次里对了 0 次。

Needs review

Test details

This test ran 1 times: 1 need attention.
Why it failed: Logic-grid reasoning was unstable

复测一致性

反复多问几次，看会不会答一半就断或偷偷换模型。 2 次都对。

Passed

Test details

This test ran 2 times: 2 passed.
This test used 313 tokens

DeepSeek 推理边界

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 416 tokens

DeepSeek 推理边界

用几道题看它的回答水平像不像官方模型。 1 次里对了 0 次。

Needs review

Test details

This test ran 1 times: 1 need attention.
Why it failed: Brand-boundary response was unclear

模型代码锚定

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 224 tokens

Model-family test: series and tier identification

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 227 tokens

Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。 1 次里对了 0 次。

Needs review

Test details

This test ran 1 times: 1 need attention.
Why it failed: Model-specific boundary response was unclear

Reviews

还没有人评论，来写第一条。

发表评论

Before you buy AI, check Mozhenzhen

Scan to view reportOpen full report

Mozhenzhen verification report · Measured with real calls

Is deepseek-v4-pro genuine? Deep check result

Report ID:MZZR2026090916082267E667Generated at：2026/09/10 00:08

Provider details AI model details

Model consistency score

Doubtful

deepseek-v4-pro 本次深度验真结果：Doubtful（73/100）。主要问题：复杂推理题答得不稳；这个型号该有的特点答不上来；会含糊地把自己说成官方原厂。

Tested byMozhenzhen

Tested modelDeepSeek V4 Pro

ProvidersDeepSeek API 型号池

Requests19

Duration1 min

Identity verdictNot verified

Reference模真真既有版本化基线

Token usage check

Reported usage is used; estimates appear only when none is reported.

Results for this test

Review API availability, model identity, response completeness, and other checks separately.

Scoring breakdown

Doubtful73/100

主要问题：复杂推理题答得不稳；这个型号该有的特点答不上来；会含糊地把自己说成官方原厂。

Can you call it, and is the model listed10 / 10

No deductions

Does the API respond properly12 / 12

No deductions

Is it the model it claims to be8 / 18

会含糊地把自己说成官方原厂（DeepSeek 推理边界） -4这个型号该有的特点答不上来（深度模型题：模型族专属边界） -6

Does it answer like the official model12 / 25

复杂推理题答得不稳（逻辑网格推理） -10这个型号该有的特点答不上来（深度模型题：模型族专属边界） -3

Is usage and billing reasonable10 / 10

No deductions

Will it keep working21 / 25

复杂推理题答得不稳（逻辑网格推理） -4

Test details

Expand any row for details; anything private has been removed

16 checks

Model list visibility

deepseek-v4-pro is visible in the API model list.

Passed

Test details

This test ran 3 times; result: Passed.

Basic call probe

The basic API call succeeded and returned a recognizable response.

Passed

Test details

This test ran 1 times; result: Passed.

Model self-identification

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 438 tokens

指令跟随

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 140 tokens

JSON 结构

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 158 tokens

标签结构复述

按官方接口的标准调用，看返回是否规范。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 273 tokens

隐藏提示词边界

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 242 tokens

品牌边界

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 394 tokens

用量数据是否完整

核对它报回来的用量和缓存计费。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 166 tokens

逻辑网格推理

用几道题看它的回答水平像不像官方模型。 1 次里对了 0 次。

Needs review

Test details

This test ran 1 times: 1 need attention.
Why it failed: Logic-grid reasoning was unstable

复测一致性

反复多问几次，看会不会答一半就断或偷偷换模型。 2 次都对。

Passed

Test details

This test ran 2 times: 2 passed.
This test used 313 tokens

DeepSeek 推理边界

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 416 tokens

DeepSeek 推理边界

用几道题看它的回答水平像不像官方模型。 1 次里对了 0 次。

Needs review

Test details

This test ran 1 times: 1 need attention.
Why it failed: Brand-boundary response was unclear

模型代码锚定

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 224 tokens

Model-family test: series and tier identification

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 227 tokens

Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。 1 次里对了 0 次。

Needs review

Test details

This test ran 1 times: 1 need attention.
Why it failed: Model-specific boundary response was unclear

Reviews

还没有人评论，来写第一条。