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。
UndeterminedBelow decision threshold
Identity could not be determined this time
The answers are not close enough to any known model, so it cannot be determined.
Brand consistency—/100
Model match score (glm-5.2)—/100
Checks0/4 Passed
- Providers
- 智谱 GLM API 型号池
- Claimed model
- glm-5.2
- Plan
- Standard verification
- Reference
- 75 official models
- Requests
- 12
- Duration
- 6 分钟
01Identity check
Behaviour compared with each official referenceIndependent sample A采样 AValidIndependent sample B采样 BInvalidIndependent sample C采样 CValidReference75 official models · 2/3 Valid
Similarity to official modelsTop 5
- glm-5.2Claimed model92%
- glm-58%
- glm-4.7<1%
- glm-4.5-air<1%
- glm-5.1<1%
02Test details
4 items · 0 passed · 4 notes · 0 failed| No. | Check | Result | Methodology |
|---|---|---|---|
| Identity check | |||
| C-01 | Independent sampling | 2 / 3 valid | Some samples could not be used for comparison |
| C-02 | Brand consistency | Pending review | Brand match score 0; below the decision threshold |
| C-03 | Model consistency | Undetermined | Model match score 0; below the decision threshold |
| C-04 | Cross-brand swap check | Needs attention | Similarity to other brands' models totals about 100% |
Cache billing check
The same long content was sent 5 times: the 1st is billed at the regular price, and from the 2nd on the repeated part should be billed at the cache price.
Cache billing ratio49.7%
有缓存优惠
同样的内容连问 5 次，从第 2 次起平均 50% 按缓存价算。
Usage this run28.0KCached tokens11.0KNon-cached tokens17.0KAverage per run5.6K
Usage reportedReportedCache billingHappenedResult有缓存优惠
Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill
Context length check
Long documents are sent tier by tier to check whether the whole document is read.
Verified up to 128K
这条线能稳定读完 128K 的内容，可以按这个长度来用。
Reference windowVerified up to 128KThe model center has no reference context window for this model yet.Tested context lengths32K / 128KTested from short to long, stopping at the first failure.
- 32KRead in full · 31.4K received
- 128KRead in full · 120.0K received
Token usage check
Reported usage is used; estimates appear only when none is reported.
Reported usage193.2KThe actual usage reported by the API; this page goes by it.Estimated usage3.0K-30.0KEstimated from this test's requests.Deviation544% aboveThe reported usage is above the estimate; check your bill.Usage checkAbove the estimateFigures are as reported by the API; your bill is authoritative.
Method: independent samples from the tested endpoint are compared against reference samples collected from official channels; billing, context and capability items come from real calls. API keys, request bodies and raw model output are not stored.
This report reflects the endpoint at the time of testing.
Reviews
还没有人评论，来写第一条。
Before you buy AI, check MozhenzhenScan to view reportOpen full report
Mozhenzhen verification report · Measured with real calls
Is glm-5.2 genuine? Verification result
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。
UndeterminedBelow decision threshold
Identity could not be determined this time
The answers are not close enough to any known model, so it cannot be determined.
Brand consistency—/100
Model match score (glm-5.2)—/100
Checks0/4 Passed
- Providers
- 智谱 GLM API 型号池
- Claimed model
- glm-5.2
- Plan
- Standard verification
- Reference
- 75 official models
- Requests
- 12
- Duration
- 6 分钟
01Identity check
Behaviour compared with each official referenceIndependent sample A采样 AValidIndependent sample B采样 BInvalidIndependent sample C采样 CValidReference75 official models · 2/3 Valid
Similarity to official modelsTop 5
- glm-5.2Claimed model92%
- glm-58%
- glm-4.7<1%
- glm-4.5-air<1%
- glm-5.1<1%
02Test details
4 items · 0 passed · 4 notes · 0 failed| No. | Check | Result | Methodology |
|---|---|---|---|
| Identity check | |||
| C-01 | Independent sampling | 2 / 3 valid | Some samples could not be used for comparison |
| C-02 | Brand consistency | Pending review | Brand match score 0; below the decision threshold |
| C-03 | Model consistency | Undetermined | Model match score 0; below the decision threshold |
| C-04 | Cross-brand swap check | Needs attention | Similarity to other brands' models totals about 100% |
Cache billing check
The same long content was sent 5 times: the 1st is billed at the regular price, and from the 2nd on the repeated part should be billed at the cache price.
Cache billing ratio49.7%
有缓存优惠
同样的内容连问 5 次，从第 2 次起平均 50% 按缓存价算。
Usage this run28.0KCached tokens11.0KNon-cached tokens17.0KAverage per run5.6K
Usage reportedReportedCache billingHappenedResult有缓存优惠
Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill
Context length check
Long documents are sent tier by tier to check whether the whole document is read.
Verified up to 128K
这条线能稳定读完 128K 的内容，可以按这个长度来用。
Reference windowVerified up to 128KThe model center has no reference context window for this model yet.Tested context lengths32K / 128KTested from short to long, stopping at the first failure.
- 32KRead in full · 31.4K received
- 128KRead in full · 120.0K received
Token usage check
Reported usage is used; estimates appear only when none is reported.
Reported usage193.2KThe actual usage reported by the API; this page goes by it.Estimated usage3.0K-30.0KEstimated from this test's requests.Deviation544% aboveThe reported usage is above the estimate; check your bill.Usage checkAbove the estimateFigures are as reported by the API; your bill is authoritative.
Method: independent samples from the tested endpoint are compared against reference samples collected from official channels; billing, context and capability items come from real calls. API keys, request bodies and raw model output are not stored.
This report reflects the endpoint at the time of testing.
Reviews
还没有人评论，来写第一条。
发表评论