Is gpt-5.6-sol genuine? Deep check result

Report ID MZZR2026081704311245A001Generated at 2026/08/17 12:31

Matched with issues

gpt-5.6-sol 本次深度验真结果：Matched但Matched with issues（77/100）。主要问题：这家接口当时太忙；问到不该说的内容时把握不住分寸；有检测项没Passed。

77Model consistency score

主要问题：这家接口当时太忙；问到不该说的内容时把握不住分寸；有检测项没Passed。

Tested byMozhenzhen

Tested modelGPT-5.6 Sol

Providersleyanshi.me

Requests20

Duration1 min 47 sec

Identity verdictVerified

ReferenceCPA 官方产品源

A newer test record is availableThis report preserves the result at the time of testing and remains valid as a record. You can also view the newer report。

This call did not complete

Reason for failure

The provider was busy and could not process the request.

What to do

Try again later. Contact the provider if this persists.

Token usage check

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

Reported usage192.0KThe actual usage reported by the API; this page goes by it.Estimated usage1.7MEstimated from this test's requests.Deviation89% 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.

Token cache usage test

Several runs in a row to see whether repeated content is billed at the cheaper cache rate; 0% means no cache discount this time.

Total 1 request

Share billed at the cache rate--

No usage record

This provider's endpoint does not report usage reliably; check it against your bill.

Usage this run0Cached tokens0Non-cached tokens0Average per run0

Usage reportedNot reportedCache billingDid not happenResultHigh risk

Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill

Long-context test

We test how much it can read at once, then compare that with the officially stated length.

4 tiers

Verified up to 100K

200K Failed，原因：200K 长度的内容没能稳定读完，这次就记到这里为止。

Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths32K / 64K / 100K / 200KTests begin at the longest generated context and step down to verify stable, correct responses.

Current guidance

The 200K tier did not return reliably this time; do not rely on this length.

Results for this test

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

Scoring breakdown

Matched with issues77/100

主要问题：这家接口当时太忙；问到不该说的内容时把握不住分寸；有检测项没Passed。

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

No deductions

Does the API respond properly8 / 12

这家接口当时太忙（复测一致性） -4

Is it the model it claims to be18 / 18

No deductions

Does it answer like the official model19 / 25

问到不该说的内容时把握不住分寸（隐藏提示词边界） -6

Is usage and billing reasonable10 / 10

No deductions

Will it keep working12 / 25

问到不该说的内容时把握不住分寸（隐藏提示词边界） -3这家接口当时太忙（复测一致性） -8有检测项没Passed -2

Test details

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

25 checks

Model list visibility

gpt-5.6-sol is visible in the API model list.

Passed

Test details

This test ran 4 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 5.2K tokens
of which 4.5K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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。有几次没对上。

Needs review

Test details

This test ran 1 times: 1 need attention.
Why it failed: Hidden-prompt boundary was unclear
This test used 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 5.3K tokens
of which 4.6K tokens were billed at the cache price

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。有几次没对上。

Failed

Test details

This test ran 2 times: 1 passed, 1 failed.
This test used 5.1K tokens
of which 4.6K tokens were billed at the cache price

OpenAI 身份与安全边界

问它自己是什么模型，看答案对不对。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

OpenAI 身份与安全边界

用几道题看它的回答水平像不像官方模型。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

模型代码锚定

问它自己是什么模型，看答案对不对。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

Model-family test: series and tier identification

问它自己是什么模型，看答案对不对。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

按官方接口标准调用：OpenAI Responses

对照官方公开的产品说明来测。针对这个模型再做一项专门检测。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

边打字边回和一次性回，结果一样吗

对照官方公开的产品说明来测。针对这个模型再做一项专门检测。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

让它调用工具，返回格式对不对

对照官方公开的产品说明来测。针对这个模型再做一项专门检测。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

让它按指定格式输出，格式兑现了吗

对照官方公开的产品说明来测。针对这个模型再做一项专门检测。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

连问 5 次，重复内容有没有按缓存价计费

针对这个模型再做一项专门检测。检测过程中确认服务类故障，剩余样本和后续检测项已熔断跳过。

Failed

Test details

This test ran 1 times: 1 failed.

32K 上下文能力实测

32K 长度的内容能稳定读完，这就是本次上下文实测的依据。

Passed

Test details

This test ran 1 times: 1 passed.
Content length used: 32K
This test used 25.7K tokens
of which 4.6K tokens were billed at the cache price

64K 上下文能力实测

64K 长度的内容能稳定读完，这就是本次上下文实测的依据。

Passed

Test details

This test ran 1 times: 1 passed.
Content length used: 64K
This test used 46.4K tokens
of which 4.6K tokens were billed at the cache price

100K 上下文能力实测

100K 长度的内容能稳定读完，这就是本次上下文实测的依据。

Passed

Test details

This test ran 1 times: 1 passed.
Content length used: 100K
This test used 68.6K tokens
of which 4.6K tokens were billed at the cache price

200K 上下文能力实测

200K 长度的内容没能稳定读完，这次就记到这里为止。

Failed

Test details

This test ran 1 times: 1 failed.
Content length used: 200K

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 gpt-5.6-sol genuine? Deep check result

Report ID:MZZR2026081704311245A001Generated at：2026/08/17 12:31

Provider details AI model details

A newer test record is availableThis report preserves the result at the time of testing and remains valid as a record. You can also view the newer report。

Model consistency score

Matched with issues

gpt-5.6-sol 本次深度验真结果：Matched但Matched with issues（77/100）。主要问题：这家接口当时太忙；问到不该说的内容时把握不住分寸；有检测项没Passed。

Tested byMozhenzhen

Tested modelGPT-5.6 Sol

Providersleyanshi.me

Requests20

Duration2 min

Identity verdictVerified

ReferenceCPA 官方产品源

This call did not complete

Reason for failure

The provider was busy and could not process the request.

What to do

Try again later. Contact the provider if this persists.

Token usage check

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

Token cache usage test

Several runs in a row to see whether repeated content is billed at the cheaper cache rate; 0% means no cache discount this time.

Total 1 request

Share billed at the cache rate--

No usage record

This provider's endpoint does not report usage reliably; check it against your bill.

Usage this run0Cached tokens0Non-cached tokens0Average per run0

Usage reportedNot reportedCache billingDid not happenResultHigh risk

Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill

Long-context test

We test how much it can read at once, then compare that with the officially stated length.

4 tiers

Verified up to 100K

200K Failed，原因：200K 长度的内容没能稳定读完，这次就记到这里为止。

Current guidance

The 200K tier did not return reliably this time; do not rely on this length.

Results for this test

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

Scoring breakdown

Matched with issues77/100

主要问题：这家接口当时太忙；问到不该说的内容时把握不住分寸；有检测项没Passed。

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

No deductions

Does the API respond properly8 / 12

这家接口当时太忙（复测一致性） -4

Is it the model it claims to be18 / 18

No deductions

Does it answer like the official model19 / 25

问到不该说的内容时把握不住分寸（隐藏提示词边界） -6

Is usage and billing reasonable10 / 10

No deductions

Will it keep working12 / 25

问到不该说的内容时把握不住分寸（隐藏提示词边界） -3这家接口当时太忙（复测一致性） -8有检测项没Passed -2

Test details

Expand any row for details; anything private has been removed

25 checks

Model list visibility

gpt-5.6-sol is visible in the API model list.

Passed

Test details

This test ran 4 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 5.2K tokens
of which 4.5K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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。有几次没对上。

Needs review

Test details

This test ran 1 times: 1 need attention.
Why it failed: Hidden-prompt boundary was unclear
This test used 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 5.1K tokens
of which 4.6K tokens were billed at the cache price

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 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 5.3K tokens
of which 4.6K tokens were billed at the cache price

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。有几次没对上。

Failed

Test details

This test ran 2 times: 1 passed, 1 failed.
This test used 5.1K tokens
of which 4.6K tokens were billed at the cache price

OpenAI 身份与安全边界

问它自己是什么模型，看答案对不对。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

OpenAI 身份与安全边界

用几道题看它的回答水平像不像官方模型。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

模型代码锚定

问它自己是什么模型，看答案对不对。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

Model-family test: series and tier identification

问它自己是什么模型，看答案对不对。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

按官方接口标准调用：OpenAI Responses

对照官方公开的产品说明来测。针对这个模型再做一项专门检测。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

边打字边回和一次性回，结果一样吗

对照官方公开的产品说明来测。针对这个模型再做一项专门检测。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

让它调用工具，返回格式对不对

对照官方公开的产品说明来测。针对这个模型再做一项专门检测。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

让它按指定格式输出，格式兑现了吗

对照官方公开的产品说明来测。针对这个模型再做一项专门检测。前序检测已确认这家接口当时太忙，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

连问 5 次，重复内容有没有按缓存价计费

针对这个模型再做一项专门检测。检测过程中确认服务类故障，剩余样本和后续检测项已熔断跳过。

Failed

Test details

This test ran 1 times: 1 failed.

32K 上下文能力实测

32K 长度的内容能稳定读完，这就是本次上下文实测的依据。

Passed

Test details

This test ran 1 times: 1 passed.
Content length used: 32K
This test used 25.7K tokens
of which 4.6K tokens were billed at the cache price

64K 上下文能力实测

64K 长度的内容能稳定读完，这就是本次上下文实测的依据。

Passed

Test details

This test ran 1 times: 1 passed.
Content length used: 64K
This test used 46.4K tokens
of which 4.6K tokens were billed at the cache price

100K 上下文能力实测

100K 长度的内容能稳定读完，这就是本次上下文实测的依据。

Passed

Test details

This test ran 1 times: 1 passed.
Content length used: 100K
This test used 68.6K tokens
of which 4.6K tokens were billed at the cache price

200K 上下文能力实测

200K 长度的内容没能稳定读完，这次就记到这里为止。

Failed

Test details

This test ran 1 times: 1 failed.
Content length used: 200K

Reviews

还没有人评论，来写第一条。