Free model verification · Redacted public report

claude-sonnet-5 deep verification model-consistency report

Report ID MZZR20260716024456A154C2Generated at 2026/07/16 10:44

Highly matched

claude-sonnet-5 deep verification result: Highly matched (100/100). All primary checks passed in this run.

100Consistency score

All primary checks passed in this run.

EvaluatorMozhenzhen

Tested modelClaude Sonnet 5

ProvidersInfistar

Samples27 probes

Duration2 min 5 sec

Verification versionV10

Identity verdictVerified

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.

Measured token usage373.5KFrom the response usage fields; this is the report's primary usage measure.Test-suite estimate74.9KPrecisely estimated from this test suite when no official baseline is available.Variance assessment399% aboveMeasured token usage is above the estimate; review billing or provider logs.Usage conclusionAbove estimateThis 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 5 times

Observed cache share64.3%

Low cache share

Cached tokens were observed, but the share is low. Review API parameters, context reuse, and billing methodology.

Observed tokens137.5KCached tokens88.4KNon-cached tokens49.1KAverage per run27.5K

Token usage recordReturnedCache fieldObservedResultNormal

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

Long-context test

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

1 samples

边界在 950K

950K 需要关注，原因：上下文保持较弱。

Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths950KTests begin at the longest generated context and step down to verify stable, correct responses.

Current guidance

950K 档暂不作为当前线路的稳定上下文参考。

A newer report is availableThis report has been superseded by a later retest.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

Highly matched100/100

All primary checks passed in this run.

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.

15 checks

Model list visibility

claude-sonnet-5 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

The basic API call succeeded and returned a recognizable response.

Passed

Test evidence

Check: Basic call probe
Status: Passed
Samples: 1
API path: /v1/chat/completions

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。全部样本Passed。

Passed

Test evidence

Check: Quick test: model self-identification
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.9K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Standard test: instruction following
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.8K
Cached tokens: 17.7K

Standard test: JSON structure

要求模型输出固定 JSON，判断结构化响应是否稳定。全部样本Passed。

Passed

Test evidence

Check: Standard test: JSON structure
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.8K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Standard test: brand boundary
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.9K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: 品牌题：Claude 思考边界
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 18.0K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Model-specific test: model-code anchoring
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 18.9K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Model-family test: series and tier identification
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 19.0K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Standard test: usage observability
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.8K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

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: 18.0K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Deep model test: family-specific boundary
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 19.3K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Deep test: retest consistency
Status: Passed
Samples: 2
Test type: Text test
Results: Passed 2 / Needs review 0 / Failed 0
Observed tokens: 35.6K
Cached tokens: 35.4K

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。全部样本Passed。

Passed

Test evidence

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: 137.5K
Cached tokens: 88.4K

专项：950K 上下文实测

950K 长度样本未形成稳定结果，本次按边界样本记录。

Needs review

Test evidence

Check: 专项：950K 上下文实测
Status: Needs review
Samples: 1
Test type: Text test
Specialty: Context test
Context tier: 950K
Needs review原因：上下文保持较弱
Results: Passed 0 / Needs review 1 / Failed 0

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-sonnet-5 deep verification model-consistency report

Report ID:MZZR20260716024456A154C2Generated at：2026/07/16 10:44

Provider details AI model details

Model consistency score

Highly matched

claude-sonnet-5 deep verification result: Highly matched (100/100). All primary checks passed in this run.

EvaluatorMozhenzhen

Tested modelClaude Sonnet 5

ProvidersInfistar

Samples27

Duration2 min

Test versionV10

Identity verdictVerified

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 5 times

Observed cache share64.3%

Low cache share

Cached tokens were observed, but the share is low. Review API parameters, context reuse, and billing methodology.

Observed tokens137.5KCached tokens88.4KNon-cached tokens49.1KAverage per run27.5K

Token usage recordReturnedCache fieldObservedResultNormal

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

Long-context test

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

1 samples

边界在 950K

950K 需要关注，原因：上下文保持较弱。

Current guidance

950K 档暂不作为当前线路的稳定上下文参考。

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

Highly matched100/100

All primary checks passed in this run.

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.

15 checks

Model list visibility

claude-sonnet-5 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

The basic API call succeeded and returned a recognizable response.

Passed

Test evidence

Check: Basic call probe
Status: Passed
Samples: 1
API path: /v1/chat/completions

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。全部样本Passed。

Passed

Test evidence

Check: Quick test: model self-identification
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.9K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Standard test: instruction following
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.8K
Cached tokens: 17.7K

Standard test: JSON structure

要求模型输出固定 JSON，判断结构化响应是否稳定。全部样本Passed。

Passed

Test evidence

Check: Standard test: JSON structure
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.8K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Standard test: brand boundary
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.9K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: 品牌题：Claude 思考边界
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 18.0K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Model-specific test: model-code anchoring
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 18.9K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Model-family test: series and tier identification
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 19.0K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Standard test: usage observability
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 17.8K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

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: 18.0K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Deep model test: family-specific boundary
Status: Passed
Samples: 1
Test type: Text test
Results: Passed 1 / Needs review 0 / Failed 0
Observed tokens: 19.3K
Cached tokens: 17.7K

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。全部样本Passed。

Passed

Test evidence

Check: Deep test: retest consistency
Status: Passed
Samples: 2
Test type: Text test
Results: Passed 2 / Needs review 0 / Failed 0
Observed tokens: 35.6K
Cached tokens: 35.4K

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。全部样本Passed。

Passed

Test evidence

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: 137.5K
Cached tokens: 88.4K

专项：950K 上下文实测

950K 长度样本未形成稳定结果，本次按边界样本记录。

Needs review

Test evidence

Check: 专项：950K 上下文实测
Status: Needs review
Samples: 1
Test type: Text test
Specialty: Context test
Context tier: 950K
Needs review原因：上下文保持较弱
Results: Passed 0 / Needs review 1 / Failed 0

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