claude-opus-4-8 本次模型一致性深度验真结果：Doubtful（65/100）。主要扣分项：模型代码锚定不稳定；复测一致性不足；模型族识别不稳定。
主要扣分项：模型代码锚定不稳定；复测一致性不足；模型族识别不稳定。
Measured API usage is shown first; official baselines or test estimates are used only when measured values are unavailable.
Observes token usage, cache fields, and reuse across rounds; 0% means no cached-token field was observed.
Cached tokens were observed, but the share is low. Review API parameters, context reuse, and billing methodology.
Shows stable responses at different context lengths and the model center reference window.
All tested context tiers (32K / 64K / 100K / 200K / 400K / 800K / 1M) returned reliably.
Review API availability, model identity, response completeness, and other checks separately.
主要扣分项：模型代码锚定不稳定；复测一致性不足；模型族识别不稳定。
Expand each check to view the redacted evidence notes.
claude-opus-4-8 is visible in the API model list.
Check: Model list visibility Status: Passed Samples: 14 API path: /v1/models Visible models: 14
The basic API call succeeded and returned a recognizable response.
Check: Basic call probe Status: Passed Samples: 1 API path: /v1/chat/completions
General test used as Mozhenzhen verification evidence for the identity dimension. All samples passed.
Check: Quick test: model self-identification Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.9K Cached tokens: 4.4K
General test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Standard test: instruction following Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.5K Cached tokens: 4.2K
General test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Standard test: JSON structure Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.5K Cached tokens: 4.2K
General test used as Mozhenzhen verification evidence for the protocol dimension. All samples passed.
Check: Standard test: tag-structure repetition Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.6K Cached tokens: 4.3K
General test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Standard test: hidden-prompt boundary Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.6K Cached tokens: 4.3K
General test used as Mozhenzhen verification evidence for the identity dimension. All samples passed.
Check: Standard test: brand boundary Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.7K Cached tokens: 4.3K
General test used as Mozhenzhen verification evidence for the usage dimension. All samples passed.
Check: Standard test: usage observability Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.5K Cached tokens: 4.2K
General test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Deep test: logic-grid reasoning Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.9K Cached tokens: 4.5K
执行 通用题，用于形成模真真验真证据，评分维度：stability。 存在样本未完全Passed。
Check: Deep test: retest consistency Status: Needs review Samples: 2 Test type: Text test Needs review原因：复测一致性不足 Results: Passed 0 / Needs review 2 / Failed 0 Observed tokens: 13.3K Cached tokens: 8.6K
Brand-specific test used as Mozhenzhen verification evidence for the identity dimension. All samples passed.
Check: Brand test: Claude hidden-reasoning evidence boundary Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.7K Cached tokens: 4.3K
Brand-specific test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Deep brand test: Claude hidden-reasoning boundary Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.6K Cached tokens: 4.3K
执行 模型级题，用于形成模真真验真证据，评分维度：identity。 存在样本未完全Passed。
Check: Model-specific test: model-code anchoring Status: Needs review Samples: 1 Test type: Text test Needs review原因：模型代码锚定不稳定 Results: Passed 0 / Needs review 1 / Failed 0 Observed tokens: 6.8K Cached tokens: 4.4K
执行 模型级题，用于形成模真真验真证据，评分维度：identity。 存在样本未完全Passed。
Check: Model-family test: series and tier identification Status: Needs review Samples: 1 Test type: Text test Needs review原因：模型族识别不稳定 Results: Passed 0 / Needs review 1 / Failed 0 Observed tokens: 6.6K Cached tokens: 4.3K
执行 模型级题，用于形成模真真验真证据，评分维度：ability。 存在样本未完全Passed。
Check: Deep model test: family-specific boundary Status: Needs review Samples: 1 Test type: Text test Needs review原因：模型专属边界表达不清 Results: Passed 0 / Needs review 1 / Failed 0 Observed tokens: 6.7K Cached tokens: 4.3K
Specialty test used as Mozhenzhen verification evidence. All samples passed.
Check: Specialty test: token cache usage over 5 rounds Status: Passed Samples: 5 Test type: Text test Specialty: Token cache usage test (may affect real billing) Results: Passed 5 / Needs review 0 / Failed 0 Observed tokens: 59.1K Cached tokens: 38.4K
32K context sample returned reliably and is included as evidence for this run.
Check: Specialty test: 32K context capability Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 32K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 36.4K Cached tokens: 23.6K
64K context sample returned reliably and is included as evidence for this run.
Check: 专项：64K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 64K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 66.2K Cached tokens: 43.0K
100K context sample returned reliably and is included as evidence for this run.
Check: 专项：100K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 100K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 98.3K Cached tokens: 63.8K
200K context sample returned reliably and is included as evidence for this run.
Check: 专项：200K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 200K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 190.0K Cached tokens: 123.5K
400K context sample returned reliably and is included as evidence for this run.
Check: 专项：400K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 400K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 373.5K Cached tokens: 242.7K
800K context sample returned reliably and is included as evidence for this run.
Check: 专项：800K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 800K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 740.4K Cached tokens: 481.2K
1M context sample returned reliably and is included as evidence for this run.
Check: 专项：1M 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 1M Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 952.3K Cached tokens: 619.0K
Be the first to leave a review.
AI service research and model verification reportclaude-opus-4-8 本次模型一致性深度验真结果：Doubtful（65/100）。主要扣分项：模型代码锚定不稳定；复测一致性不足；模型族识别不稳定。
Measured API usage is shown first; official baselines or test estimates are used only when measured values are unavailable.
Observes token usage, cache fields, and reuse across rounds; 0% means no cached-token field was observed.
Cached tokens were observed, but the share is low. Review API parameters, context reuse, and billing methodology.
Shows stable responses at different context lengths and the model center reference window.
All tested context tiers (32K / 64K / 100K / 200K / 400K / 800K / 1M) returned reliably.
Review API availability, model identity, response completeness, and other checks separately.
主要扣分项：模型代码锚定不稳定；复测一致性不足；模型族识别不稳定。
Expand each check to view the redacted evidence notes.
claude-opus-4-8 is visible in the API model list.
Check: Model list visibility Status: Passed Samples: 14 API path: /v1/models Visible models: 14
The basic API call succeeded and returned a recognizable response.
Check: Basic call probe Status: Passed Samples: 1 API path: /v1/chat/completions
General test used as Mozhenzhen verification evidence for the identity dimension. All samples passed.
Check: Quick test: model self-identification Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.9K Cached tokens: 4.4K
General test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Standard test: instruction following Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.5K Cached tokens: 4.2K
General test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Standard test: JSON structure Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.5K Cached tokens: 4.2K
General test used as Mozhenzhen verification evidence for the protocol dimension. All samples passed.
Check: Standard test: tag-structure repetition Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.6K Cached tokens: 4.3K
General test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Standard test: hidden-prompt boundary Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.6K Cached tokens: 4.3K
General test used as Mozhenzhen verification evidence for the identity dimension. All samples passed.
Check: Standard test: brand boundary Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.7K Cached tokens: 4.3K
General test used as Mozhenzhen verification evidence for the usage dimension. All samples passed.
Check: Standard test: usage observability Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.5K Cached tokens: 4.2K
General test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Deep test: logic-grid reasoning Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.9K Cached tokens: 4.5K
执行 通用题，用于形成模真真验真证据，评分维度：stability。 存在样本未完全Passed。
Check: Deep test: retest consistency Status: Needs review Samples: 2 Test type: Text test Needs review原因：复测一致性不足 Results: Passed 0 / Needs review 2 / Failed 0 Observed tokens: 13.3K Cached tokens: 8.6K
Brand-specific test used as Mozhenzhen verification evidence for the identity dimension. All samples passed.
Check: Brand test: Claude hidden-reasoning evidence boundary Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.7K Cached tokens: 4.3K
Brand-specific test used as Mozhenzhen verification evidence for the ability dimension. All samples passed.
Check: Deep brand test: Claude hidden-reasoning boundary Status: Passed Samples: 1 Test type: Text test Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 6.6K Cached tokens: 4.3K
执行 模型级题，用于形成模真真验真证据，评分维度：identity。 存在样本未完全Passed。
Check: Model-specific test: model-code anchoring Status: Needs review Samples: 1 Test type: Text test Needs review原因：模型代码锚定不稳定 Results: Passed 0 / Needs review 1 / Failed 0 Observed tokens: 6.8K Cached tokens: 4.4K
执行 模型级题，用于形成模真真验真证据，评分维度：identity。 存在样本未完全Passed。
Check: Model-family test: series and tier identification Status: Needs review Samples: 1 Test type: Text test Needs review原因：模型族识别不稳定 Results: Passed 0 / Needs review 1 / Failed 0 Observed tokens: 6.6K Cached tokens: 4.3K
执行 模型级题，用于形成模真真验真证据，评分维度：ability。 存在样本未完全Passed。
Check: Deep model test: family-specific boundary Status: Needs review Samples: 1 Test type: Text test Needs review原因：模型专属边界表达不清 Results: Passed 0 / Needs review 1 / Failed 0 Observed tokens: 6.7K Cached tokens: 4.3K
Specialty test used as Mozhenzhen verification evidence. All samples passed.
Check: Specialty test: token cache usage over 5 rounds Status: Passed Samples: 5 Test type: Text test Specialty: Token cache usage test (may affect real billing) Results: Passed 5 / Needs review 0 / Failed 0 Observed tokens: 59.1K Cached tokens: 38.4K
32K context sample returned reliably and is included as evidence for this run.
Check: Specialty test: 32K context capability Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 32K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 36.4K Cached tokens: 23.6K
64K context sample returned reliably and is included as evidence for this run.
Check: 专项：64K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 64K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 66.2K Cached tokens: 43.0K
100K context sample returned reliably and is included as evidence for this run.
Check: 专项：100K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 100K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 98.3K Cached tokens: 63.8K
200K context sample returned reliably and is included as evidence for this run.
Check: 专项：200K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 200K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 190.0K Cached tokens: 123.5K
400K context sample returned reliably and is included as evidence for this run.
Check: 专项：400K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 400K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 373.5K Cached tokens: 242.7K
800K context sample returned reliably and is included as evidence for this run.
Check: 专项：800K 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 800K Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 740.4K Cached tokens: 481.2K
1M context sample returned reliably and is included as evidence for this run.
Check: 专项：1M 上下文能力实测 Status: Passed Samples: 1 Test type: Text test Specialty: Context test Context tier: 1M Results: Passed 1 / Needs review 0 / Failed 0 Observed tokens: 952.3K Cached tokens: 619.0K
Be the first to leave a review.