Free model verification · Redacted public report

claude-opus-4-8[1m] quick verification model-consistency report

Report ID MZZR202607010410347505ECE2B4约收录时间 2026/06/22 16:45:07

Doubtful

claude-opus-4-8[1m] 本次模型一致性快速验真结果：Doubtful，建议结合更多样本继续复测。样本 12 条。

72Consistency score

部分检测项存在疑点，建议结合更多样本继续复测。

EvaluatorMozhenzhen

Tested modelClaude Opus 4.8

ProvidersHiyo API

Samples12 probes

Duration--

Verification versionmzz.report_semantic_normalization.2026-07-01

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 usage147Uses 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.

Model authenticity score

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

Scoring breakdown

Doubtful72/100

部分检测项存在疑点，建议结合更多样本继续复测。

基础可调用14 / 20

No deductions

接口规范与计量10 / 20

Token 用量：Failed消息标识规范：Failed

模型身份一致性28 / 35

行为签名验证：Failed

能力项真实性3 / 15

PDF文档识别：Failed长上下文真实性：未形成明确结论

响应完整性10 / 10

No deductions

Test details

Expand each check to view the redacted evidence notes.

12 checks

行为签名验证

行为签名验证：检测Failed。

Failed

Test evidence

Check: 行为签名验证
Status: Failed
Samples: 1

模型一致性

模型一致性：检测Passed。

Passed

Test evidence

Check: 模型一致性
Status: Passed
Samples: 1

身份一致性

身份一致性：检测Passed。

Passed

Test evidence

Check: 身份一致性
Status: Passed
Samples: 1

响应完整性

响应完整性：检测Passed。

Passed

Test evidence

Check: 响应完整性
Status: Passed
Samples: 1

知识准确度

知识准确度：检测Passed。

Passed

Test evidence

Check: 知识准确度
Status: Passed
Samples: 1

长上下文真实性

长上下文真实性：暂未形成明确结论。

Insufficient evidence

Test evidence

Check: 长上下文真实性
Status: Insufficient evidence
Samples: 1

消息标识规范

消息标识规范：检测Failed。

Failed

Test evidence

Check: 消息标识规范
Status: Failed
Samples: 1

PDF文档识别

PDF文档识别：检测Failed。

Failed

Test evidence

Check: PDF文档识别
Status: Failed
Samples: 1

协议规范性

协议规范性：检测Passed。

Passed

Test evidence

Check: 协议规范性
Status: Passed
Samples: 1

结构化输出

结构化输出：检测Passed。

Passed

Test evidence

Check: 结构化输出
Status: Passed
Samples: 1

思维签名验证

思维签名验证：检测Passed。

Passed

Test evidence

Check: 思维签名验证
Status: Passed
Samples: 1

Token usage

Token 用量：检测Failed。

Failed

Test evidence

Check: Token usage
Status: Failed
Samples: 1

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-4-8[1m] quick verification model-consistency report

Report ID:MZZR202607010410347505ECE2B4约收录时间：2026/06/22 16:45:07

Provider details AI model details

Model consistency score

Doubtful

claude-opus-4-8[1m] 本次模型一致性快速验真结果：Doubtful，建议结合更多样本继续复测。样本 12 条。

EvaluatorMozhenzhen

Tested modelClaude Opus 4.8

ProvidersHiyo API

Samples12

Duration--

Test versionmzz.report_semantic_normalization.2026-07-01

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.

Model authenticity score

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

Scoring breakdown

Doubtful72/100

部分检测项存在疑点，建议结合更多样本继续复测。

基础可调用14 / 20

No deductions

接口规范与计量10 / 20

Token 用量：Failed消息标识规范：Failed

模型身份一致性28 / 35

行为签名验证：Failed

能力项真实性3 / 15

PDF文档识别：Failed长上下文真实性：未形成明确结论

响应完整性10 / 10

No deductions

Test details

Expand each check to view the redacted evidence notes.

12 checks

行为签名验证

行为签名验证：检测Failed。

Failed

Test evidence

Check: 行为签名验证
Status: Failed
Samples: 1

模型一致性

模型一致性：检测Passed。

Passed

Test evidence

Check: 模型一致性
Status: Passed
Samples: 1

身份一致性

身份一致性：检测Passed。

Passed

Test evidence

Check: 身份一致性
Status: Passed
Samples: 1

响应完整性

响应完整性：检测Passed。

Passed

Test evidence

Check: 响应完整性
Status: Passed
Samples: 1

知识准确度

知识准确度：检测Passed。

Passed

Test evidence

Check: 知识准确度
Status: Passed
Samples: 1

长上下文真实性

长上下文真实性：暂未形成明确结论。

Insufficient evidence

Test evidence

Check: 长上下文真实性
Status: Insufficient evidence
Samples: 1

消息标识规范

消息标识规范：检测Failed。

Failed

Test evidence

Check: 消息标识规范
Status: Failed
Samples: 1

PDF文档识别

PDF文档识别：检测Failed。

Failed

Test evidence

Check: PDF文档识别
Status: Failed
Samples: 1

协议规范性

协议规范性：检测Passed。

Passed

Test evidence

Check: 协议规范性
Status: Passed
Samples: 1

结构化输出

结构化输出：检测Passed。

Passed

Test evidence

Check: 结构化输出
Status: Passed
Samples: 1

思维签名验证

思维签名验证：检测Passed。

Passed

Test evidence

Check: 思维签名验证
Status: Passed
Samples: 1

Token usage

Token 用量：检测Failed。

Failed

Test evidence

Check: Token usage
Status: Failed
Samples: 1

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