deepseek-v4-pro 本次标准验真结果：Doubtful（67/100）。主要问题：问它是哪个型号时答案会变；不太听指令，让它怎么答它不照做；它不报回用量，没法核对扣费。
主要问题：问它是哪个型号时答案会变；不太听指令，让它怎么答它不照做；它不报回用量，没法核对扣费。
Reported usage is used; estimates appear only when none is reported.
Review API availability, model identity, response completeness, and other checks separately.
主要问题：问它是哪个型号时答案会变；不太听指令，让它怎么答它不照做；它不报回用量，没法核对扣费。
Expand any row for details; anything private has been removed.
deepseek-v4-pro is visible in the API model list.
This test ran 2 times; result: Passed.
The basic API call succeeded and returned a recognizable response.
This test ran 1 times; result: Passed.
Asked the model to identify itself; all 1 responses matched the expected name.
This test ran 1 times: 1 passed. This test used 669 tokens of which 420 tokens were billed at the cache price
用几道题看它的回答水平像不像官方模型。 有几次没对上。
This test ran 1 times: 1 need attention. Why it failed: Instruction following was unstable This test used 715 tokens of which 420 tokens were billed at the cache price
用几道题看它的回答水平像不像官方模型。 1 次都对。
This test ran 1 times: 1 passed. This test used 482 tokens of which 128 tokens were billed at the cache price
按官方接口的标准调用，看返回是否规范。 1 次都对。
This test ran 1 times: 1 passed. This test used 536 tokens of which 420 tokens were billed at the cache price
用几道题看它的回答水平像不像官方模型。 1 次都对。
This test ran 1 times: 1 passed. This test used 591 tokens of which 256 tokens were billed at the cache price
问它自己是什么模型，看答案对不对。 有几次没对上。
This test ran 1 times: 1 need attention. Why it failed: Brand-boundary response was unclear This test used 790 tokens of which 128 tokens were billed at the cache price
核对它报回来的用量和缓存计费。 有几次没对上。
This test ran 1 times: 1 need attention. Why it failed: Usage fields were not observable This test used 733 tokens
Asked the model to identify itself; all 1 responses matched the expected name.
This test ran 1 times: 1 passed. This test used 989 tokens of which 420 tokens were billed at the cache price
问它自己是什么模型，看答案对不对。 有几次没对上。
This test ran 1 times: 1 need attention. Why it failed: Model-code anchoring was unstable This test used 1.0K tokens of which 128 tokens were billed at the cache price
Asked the model to identify itself; all 1 responses matched the expected name.
This test ran 1 times: 1 passed. This test used 885 tokens of which 128 tokens were billed at the cache price
还没有人评论，来写第一条。
Before you buy AI, check Mozhenzhendeepseek-v4-pro 本次标准验真结果：Doubtful（67/100）。主要问题：问它是哪个型号时答案会变；不太听指令，让它怎么答它不照做；它不报回用量，没法核对扣费。
Reported usage is used; estimates appear only when none is reported.
Review API availability, model identity, response completeness, and other checks separately.
主要问题：问它是哪个型号时答案会变；不太听指令，让它怎么答它不照做；它不报回用量，没法核对扣费。
Expand any row for details; anything private has been removed
deepseek-v4-pro is visible in the API model list.
This test ran 2 times; result: Passed.
The basic API call succeeded and returned a recognizable response.
This test ran 1 times; result: Passed.
Asked the model to identify itself; all 1 responses matched the expected name.
This test ran 1 times: 1 passed. This test used 669 tokens of which 420 tokens were billed at the cache price
用几道题看它的回答水平像不像官方模型。 有几次没对上。
This test ran 1 times: 1 need attention. Why it failed: Instruction following was unstable This test used 715 tokens of which 420 tokens were billed at the cache price
用几道题看它的回答水平像不像官方模型。 1 次都对。
This test ran 1 times: 1 passed. This test used 482 tokens of which 128 tokens were billed at the cache price
按官方接口的标准调用，看返回是否规范。 1 次都对。
This test ran 1 times: 1 passed. This test used 536 tokens of which 420 tokens were billed at the cache price
用几道题看它的回答水平像不像官方模型。 1 次都对。
This test ran 1 times: 1 passed. This test used 591 tokens of which 256 tokens were billed at the cache price
问它自己是什么模型，看答案对不对。 有几次没对上。
This test ran 1 times: 1 need attention. Why it failed: Brand-boundary response was unclear This test used 790 tokens of which 128 tokens were billed at the cache price
核对它报回来的用量和缓存计费。 有几次没对上。
This test ran 1 times: 1 need attention. Why it failed: Usage fields were not observable This test used 733 tokens
Asked the model to identify itself; all 1 responses matched the expected name.
This test ran 1 times: 1 passed. This test used 989 tokens of which 420 tokens were billed at the cache price
问它自己是什么模型，看答案对不对。 有几次没对上。
This test ran 1 times: 1 need attention. Why it failed: Model-code anchoring was unstable This test used 1.0K tokens of which 128 tokens were billed at the cache price
Asked the model to identify itself; all 1 responses matched the expected name.
This test ran 1 times: 1 passed. This test used 885 tokens of which 128 tokens were billed at the cache price
还没有人评论，来写第一条。
发表评论