Free model verification · Redacted public report

claude-opus-4-6 deep verification model-consistency report

Report ID MZZR20260719023916842566Generated at 2026/07/19 10:39

Inconclusive

claude-opus-4-6 本次模型一致性深度验真结果：Inconclusive（暂无评分）。接口鉴权、额度、中继、源站、网关或上游服务状态异常，本轮未进入模型真实性评分。

待确认Consistency score

接口鉴权、额度、中继、源站、网关或上游服务状态异常，本轮未进入模型真实性评分。

EvaluatorMozhenzhen

Tested modelClaude Opus 4.6

ProvidersInfistar

Samples9 probes

Duration2 sec

Verification versionV10

Identity verdictNot verified

Verification basisMozhenzhen versioned baseline

Token usage

Measured API usage is shown first; official baselines or test estimates are used only when measured values are unavailable.

Estimated token usage74.9KUses the test-suite estimate when measured usage is unavailable.Variance assessmentNone本报告有题包预计 Token，但当前接口没有返回实际用量。Usage conclusion只看到预计This reflects usage observability, not the final billed amount.

Token cache usage test

Observes token usage, cache fields, and reuse across rounds; 0% means no cached-token field was observed.

Tested 0 times

Observed cache share--

暂未观测到用量记录

当前接口没有稳定返回 Token 用量记录，建议结合账单明细或接口日志复核。

Observed tokens0Cached tokens0Non-cached tokens0Average per run--

Token usage recordNot returnedCache fieldNot observedResultNormal

Cache share by testRepresents the API-reported cache share, not the final billing discount.

No per-test records are available; only the aggregate result is shown.

Long-context test

Shows stable responses at different context lengths and the model center reference window.

7 samples

未形成稳定样本

基础调用未成功（接口鉴权或权限异常），长上下文专项已跳过。

Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths950K / 800K / 400K / 200K / 100K / 64K / 32KTests begin at the longest generated context and step down to verify stable, correct responses.

Current guidance

基础调用未成功（接口鉴权或权限异常），长上下文专项已跳过。

A newer report is availableThis report has been superseded by a later retest. View the latest report。

Model authenticity score

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

Scoring breakdown

Inconclusive待确认

接口鉴权、额度、中继、源站、网关或上游服务状态异常，本轮未进入模型真实性评分。

Callability and model visibility10 / 10

No deductions

Protocol and response structure12 / 12

No deductions

Identity and model match18 / 18

No deductions

Core capabilities and model-specific tests25 / 25

No deductions

Usage and billing consistency10 / 10

No deductions

Reliability and availability25 / 25

No deductions

Test details

Expand each check to view the redacted evidence notes.

21 checks

Model list visibility

claude-opus-4-6 is visible in the API model list.

Passed

Test evidence

Check: Model list visibility
Status: Passed
Samples: 8
API path: /v1/models
Visible models: 8

Basic call probe

基础调用未成功，可能是 Key 权限、额度、接口路径或模型能力类型问题。

Needs review

Test evidence

Check: Basic call probe
Status: Needs review
Samples: 1
Needs review原因：接口鉴权或权限异常

Quick test: model self-identification

直接询问模型身份，作为低权重红旗信号；自报只能提示明显不一致，不能单独证明官方身份。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Quick test: model self-identification
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Standard test: instruction following

要求模型按指定标记回复，判断基础指令跟随和响应可控性。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Standard test: instruction following
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Standard test: JSON structure

要求模型输出固定 JSON，判断结构化响应是否稳定。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Standard test: JSON structure
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Standard test: brand boundary

要求模型不要伪造官方身份，判断品牌表述是否克制。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Standard test: brand boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

品牌题：Claude 思考边界

观察模型是否会克制说明隐藏思考和签名特征不能被随意伪造。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 品牌题：Claude 思考边界
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Model-specific test: model-code anchoring

要求模型把本次被检测模型代码、品牌归类和固定标记写入 JSON，便于应用层精确校验。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Model-specific test: model-code anchoring
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Model-family test: series and tier identification

按模型代码识别系列或档位，覆盖 Opus/Sonnet/Haiku、GPT/o/Codex、Gemini Pro/Flash、GLM、Kimi、MiniMax 等模型族。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Model-family test: series and tier identification
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Standard test: usage observability

要求短输出并检查响应 usage 是否可被应用层读取，支撑预计消耗与实际消耗对照。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Standard test: usage observability
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Deep brand test: Claude hidden-reasoning boundary

观察模型是否会克制处理隐藏思考、系统提示和签名特征，不伪造 Claude 专属内部证据。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Deep brand test: Claude hidden-reasoning boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Deep model test: family-specific boundary

针对当前品牌和模型族补充独特边界题，避免只用通用题判断高价值模型。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Deep model test: family-specific boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Deep test: retest consistency

同一低温题连续复测两次，观察是否能保持一致响应。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Deep test: retest consistency
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Specialty test: token cache usage over 5 rounds

同一长前缀连续请求 5 次，应用层观察 usage、cache usage、token 消耗和费用风险。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Specialty test: token cache usage over 5 rounds
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Token cache usage test (may affect real billing)
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：950K 上下文实测

构造接近 950K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：950K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：800K 上下文实测

构造接近 800K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：800K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：400K 上下文实测

构造接近 400K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：400K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：200K 上下文实测

构造接近 200K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：200K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：100K 上下文实测

构造接近 100K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：100K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：64K 上下文实测

构造接近 64K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：64K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：32K 上下文实测

构造接近 32K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：32K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Report comments

No public reviews

Be the first to leave a review.

Post an anonymous comment

Rating

5 points

This reportReviews

Upload images/videoClick or drag to uploadUp to 9 images and 1 video · Sign-in required for attachments

AI service research and model verification report

Scan to view reportOpen full report

Free model verification · Supports all text models

claude-opus-4-6 deep verification model-consistency report

Report ID:MZZR20260719023916842566Generated at：2026/07/19 10:39

Provider details AI model details

Model consistency score

Inconclusive

EvaluatorMozhenzhen

Tested modelClaude Opus 4.6

ProvidersInfistar

Samples9

Duration2 sec

Test versionV10

Identity verdictNot verified

Verification basisMozhenzhen versioned baseline

Token usage

Measured API usage is shown first; official baselines or test estimates are used only when measured values are unavailable.

Token cache usage test

Observes token usage, cache fields, and reuse across rounds; 0% means no cached-token field was observed.

Tested 0 times

Observed cache share--

暂未观测到用量记录

当前接口没有稳定返回 Token 用量记录，建议结合账单明细或接口日志复核。

Observed tokens0Cached tokens0Non-cached tokens0Average per run--

Token usage recordNot returnedCache fieldNot observedResultNormal

Cache share by testRepresents the API-reported cache share, not the final billing discount.

No per-test records are available; only the aggregate result is shown.

Long-context test

Shows stable responses at different context lengths and the model center reference window.

7 samples

未形成稳定样本

基础调用未成功（接口鉴权或权限异常），长上下文专项已跳过。

Current guidance

基础调用未成功（接口鉴权或权限异常），长上下文专项已跳过。

A newer report is availableThis report has been superseded by a later retest. View the latest report。

Model authenticity score

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

Scoring breakdown

Inconclusive待确认

接口鉴权、额度、中继、源站、网关或上游服务状态异常，本轮未进入模型真实性评分。

Callability and model visibility10 / 10

No deductions

Protocol and response structure12 / 12

No deductions

Identity and model match18 / 18

No deductions

Core capabilities and model-specific tests25 / 25

No deductions

Usage and billing consistency10 / 10

No deductions

Reliability and availability25 / 25

No deductions

Test details

Expand each check to view the redacted evidence notes.

21 checks

Model list visibility

claude-opus-4-6 is visible in the API model list.

Passed

Test evidence

Check: Model list visibility
Status: Passed
Samples: 8
API path: /v1/models
Visible models: 8

Basic call probe

基础调用未成功，可能是 Key 权限、额度、接口路径或模型能力类型问题。

Needs review

Test evidence

Check: Basic call probe
Status: Needs review
Samples: 1
Needs review原因：接口鉴权或权限异常

Quick test: model self-identification

Skipped

Test evidence

Check: Quick test: model self-identification
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Standard test: instruction following

要求模型按指定标记回复，判断基础指令跟随和响应可控性。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Standard test: instruction following
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Standard test: JSON structure

要求模型输出固定 JSON，判断结构化响应是否稳定。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Standard test: JSON structure
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Standard test: brand boundary

要求模型不要伪造官方身份，判断品牌表述是否克制。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Standard test: brand boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

品牌题：Claude 思考边界

观察模型是否会克制说明隐藏思考和签名特征不能被随意伪造。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 品牌题：Claude 思考边界
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Model-specific test: model-code anchoring

要求模型把本次被检测模型代码、品牌归类和固定标记写入 JSON，便于应用层精确校验。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Model-specific test: model-code anchoring
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Model-family test: series and tier identification

Skipped

Test evidence

Check: Model-family test: series and tier identification
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Standard test: usage observability

要求短输出并检查响应 usage 是否可被应用层读取，支撑预计消耗与实际消耗对照。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Standard test: usage observability
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Deep brand test: Claude hidden-reasoning boundary

观察模型是否会克制处理隐藏思考、系统提示和签名特征，不伪造 Claude 专属内部证据。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Deep brand test: Claude hidden-reasoning boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Deep model test: family-specific boundary

针对当前品牌和模型族补充独特边界题，避免只用通用题判断高价值模型。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Deep model test: family-specific boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Deep test: retest consistency

同一低温题连续复测两次，观察是否能保持一致响应。基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Deep test: retest consistency
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Specialty test: token cache usage over 5 rounds

同一长前缀连续请求 5 次，应用层观察 usage、cache usage、token 消耗和费用风险。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: Specialty test: token cache usage over 5 rounds
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Token cache usage test (may affect real billing)
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：950K 上下文实测

构造接近 950K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：950K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：800K 上下文实测

构造接近 800K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：800K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：400K 上下文实测

构造接近 400K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：400K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：200K 上下文实测

构造接近 200K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：200K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：100K 上下文实测

构造接近 100K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：100K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：64K 上下文实测

构造接近 64K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：64K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

专项：32K 上下文实测

构造接近 32K 的上下文，要求模型同时提取开头、中段、末尾锚点。基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped

Test evidence

Check: 专项：32K 上下文实测
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Latest user reviews

No public reviews

Be the first to leave a review.

Comments and feedback on this report

Rating

5 points

This reportReviews

Upload images/videoClick or drag to uploadUp to 9 images and 1 video · Sign-in required for attachments