Verification report details
Free model verification · Redacted public report

gpt-5.6-sol deep verification model-consistency report

Report ID MZZR20260805073831B71DACGenerated at 2026/08/05 15:38

Matched

gpt-5.6-sol deep verification result: Matched (86/100). Main deductions: Origin connection interrupted; Failed evidence items were found.

86Consistency score

主要扣分项：源站连接中断；存在Failed证据项。

EvaluatorMozhenzhen
Tested modelGPT-5.6 Sol
Providers聚光AI
Samples113 probes
Duration49 sec
Verification versionV11
Identity verdictVerified
Verification basisCPA 官方产品源

Token usage

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

Measured token usage4.4KFrom 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 assessment94% belowMeasured token usage is below the estimate, possibly due to tokenizer, compression, or usage-reporting differences.Usage conclusionBelow 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 1 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 run0
Token usage recordNot returnedCache fieldNot observedResultHigh risk
Cache share by testRepresents the API-reported cache share, not the final billing discount.
100%75%50%25%01次：未返回用量数据未返回1times
Long-context test

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

1 samples
边界在 32K

32K Failed，原因：32K 长度样本未形成稳定结果，本次按边界样本记录。

Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance

32K 档暂不作为当前线路的稳定上下文参考。

Model authenticity score

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

Scoring breakdown

Matched86/100

主要扣分项：源站连接中断；存在Failed证据项。

Callability and model visibility10 / 10
No deductions
Protocol and response structure8 / 12
源站连接中断（快速题：模型身份自报） -4
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 availability15 / 25
源站连接中断（快速题：模型身份自报） -8存在Failed证据项 -2

Test details

Expand each check to view the redacted evidence notes.

22 checks
Model list visibility

gpt-5.6-sol is visible in the API model list.

Passed
Test evidence
Check: Model list visibility
Status: Passed
Samples: 109
API path: /v1/models
Visible models: 109
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

执行 通用题，用于形成模真真验真证据，评分维度：identity。 存在样本未完全Passed。

Failed
Test evidence
Check: Quick test: model self-identification
Status: Failed
Samples: 1
Test type: Text test
Results: Passed 0 / Needs review 0 / Failed 1
Standard test: instruction following

执行 通用题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: instruction following
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: JSON structure

执行 通用题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: JSON structure
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: tag-structure repetition

执行 通用题，用于形成模真真验真证据，评分维度：protocol。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: tag-structure repetition
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: hidden-prompt boundary

执行 通用题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: hidden-prompt boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: brand boundary

执行 通用题，用于形成模真真验真证据，评分维度：identity。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: brand boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: usage observability

执行 通用题，用于形成模真真验真证据，评分维度：usage。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: usage observability
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Deep test: logic-grid reasoning

执行 通用题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Deep test: logic-grid reasoning
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Deep test: retest consistency

执行 通用题，用于形成模真真验真证据，评分维度：stability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Deep test: retest consistency
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
品牌题：OpenAI 身份与安全边界 证据边界

执行 品牌题，用于形成模真真验真证据，评分维度：identity。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 品牌题：OpenAI 身份与安全边界 证据边界
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
深度品牌题：OpenAI 身份与安全边界

执行 品牌题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 深度品牌题：OpenAI 身份与安全边界
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Model-specific test: model-code anchoring

执行 模型级题，用于形成模真真验真证据，评分维度：identity。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Model-specific test: model-code anchoring
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Model-family test: series and tier identification

执行 模型级题，用于形成模真真验真证据，评分维度：identity。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Model-family test: series and tier identification
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Deep model test: family-specific boundary

执行 模型级题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Deep model test: family-specific boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
正式来源必检：专项：OpenAI Responses 原生协议

按CPA 官方产品源确定的方法执行。执行 专项题，用于形成模真真验真证据。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 正式来源必检：专项：OpenAI Responses 原生协议
Status: Skipped
Samples: 0
跳过原因：service_failure_circuit_breaker
正式来源必检：专项：流式 / 非流式一致性

按CPA 官方产品源确定的方法执行。执行 专项题，用于形成模真真验真证据。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 正式来源必检：专项：流式 / 非流式一致性
Status: Skipped
Samples: 0
跳过原因：service_failure_circuit_breaker
正式来源必检：专项：工具调用结构

按CPA 官方产品源确定的方法执行。执行 专项题，用于形成模真真验真证据。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 正式来源必检：专项：工具调用结构
Status: Skipped
Samples: 0
跳过原因：service_failure_circuit_breaker
正式来源必检：专项：JSON Schema 结构化输出

按CPA 官方产品源确定的方法执行。执行 专项题，用于形成模真真验真证据。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 正式来源必检：专项：JSON Schema 结构化输出
Status: Skipped
Samples: 0
跳过原因：service_failure_circuit_breaker
Specialty test: token cache usage over 5 rounds

执行 专项题，用于形成模真真验真证据。 检测过程中确认服务类故障，剩余样本和后续检测项已熔断跳过。

Failed
Test evidence
Check: Specialty test: token cache usage over 5 rounds
Status: Failed
Samples: 1
Test type: Text test
Specialty: Token cache usage test (may affect real billing)
Results: Passed 0 / Needs review 0 / Failed 1
Specialty test: 32K context capability

32K 长度样本未形成稳定结果，本次按边界样本记录。

Failed
Test evidence
Check: Specialty test: 32K context capability
Status: Failed
Samples: 1
Test type: Text test
Specialty: Context test
Context tier: 32K
Results: Passed 0 / Needs review 0 / Failed 1

Report comments

No public reviews

Be the first to leave a review.

Post an anonymous comment

Rating
5 points
Upload images/video
Home/Model verification/Verification reports
MozhenzhenAI service research and model verification report
Scan to view reportOpen full report
Free model verification · Supports all text models

gpt-5.6-sol deep verification model-consistency report

Report ID:MZZR20260805073831B71DACGenerated at：2026/08/05 15:38
Provider detailsAI model details
Model consistency score

Matched

gpt-5.6-sol deep verification result: Matched (86/100). Main deductions: Origin connection interrupted; Failed evidence items were found.

EvaluatorMozhenzhen
Tested modelGPT-5.6 Sol
Providers聚光AI
Samples113
Duration49 sec
Test versionV11
Identity verdictVerified
Verification basisCPA 官方产品源

Token usage

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

Measured token usage4.4KFrom 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 assessment94% belowMeasured token usage is below the estimate, possibly due to tokenizer, compression, or usage-reporting differences.Usage conclusionBelow 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 1 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 run0
Token usage recordNot returnedCache fieldNot observedResultHigh risk
Cache share by testRepresents the API-reported cache share, not the final billing discount.
100%75%50%25%01次：未返回用量数据未返回1times
Long-context test

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

1 samples
边界在 32K

32K Failed，原因：32K 长度样本未形成稳定结果，本次按边界样本记录。

Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance

32K 档暂不作为当前线路的稳定上下文参考。

Model authenticity score

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

Scoring breakdown

Matched86/100

主要扣分项：源站连接中断；存在Failed证据项。

Callability and model visibility10 / 10
No deductions
Protocol and response structure8 / 12
源站连接中断（快速题：模型身份自报） -4
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 availability15 / 25
源站连接中断（快速题：模型身份自报） -8存在Failed证据项 -2

Test details

Expand each check to view the redacted evidence notes.

22 checks
Model list visibility

gpt-5.6-sol is visible in the API model list.

Passed
Test evidence
Check: Model list visibility
Status: Passed
Samples: 109
API path: /v1/models
Visible models: 109
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

执行 通用题，用于形成模真真验真证据，评分维度：identity。 存在样本未完全Passed。

Failed
Test evidence
Check: Quick test: model self-identification
Status: Failed
Samples: 1
Test type: Text test
Results: Passed 0 / Needs review 0 / Failed 1
Standard test: instruction following

执行 通用题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: instruction following
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: JSON structure

执行 通用题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: JSON structure
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: tag-structure repetition

执行 通用题，用于形成模真真验真证据，评分维度：protocol。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: tag-structure repetition
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: hidden-prompt boundary

执行 通用题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: hidden-prompt boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: brand boundary

执行 通用题，用于形成模真真验真证据，评分维度：identity。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: brand boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Standard test: usage observability

执行 通用题，用于形成模真真验真证据，评分维度：usage。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Standard test: usage observability
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Deep test: logic-grid reasoning

执行 通用题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Deep test: logic-grid reasoning
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Deep test: retest consistency

执行 通用题，用于形成模真真验真证据，评分维度：stability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Deep test: retest consistency
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
品牌题：OpenAI 身份与安全边界 证据边界

执行 品牌题，用于形成模真真验真证据，评分维度：identity。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 品牌题：OpenAI 身份与安全边界 证据边界
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
深度品牌题：OpenAI 身份与安全边界

执行 品牌题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 深度品牌题：OpenAI 身份与安全边界
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Model-specific test: model-code anchoring

执行 模型级题，用于形成模真真验真证据，评分维度：identity。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Model-specific test: model-code anchoring
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Model-family test: series and tier identification

执行 模型级题，用于形成模真真验真证据，评分维度：identity。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Model-family test: series and tier identification
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
Deep model test: family-specific boundary

执行 模型级题，用于形成模真真验真证据，评分维度：ability。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: Deep model test: family-specific boundary
Status: Skipped
Samples: 0
Test type: Text test
跳过原因：service_failure_circuit_breaker
正式来源必检：专项：OpenAI Responses 原生协议

按CPA 官方产品源确定的方法执行。执行 专项题，用于形成模真真验真证据。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 正式来源必检：专项：OpenAI Responses 原生协议
Status: Skipped
Samples: 0
跳过原因：service_failure_circuit_breaker
正式来源必检：专项：流式 / 非流式一致性

按CPA 官方产品源确定的方法执行。执行 专项题，用于形成模真真验真证据。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 正式来源必检：专项：流式 / 非流式一致性
Status: Skipped
Samples: 0
跳过原因：service_failure_circuit_breaker
正式来源必检：专项：工具调用结构

按CPA 官方产品源确定的方法执行。执行 专项题，用于形成模真真验真证据。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 正式来源必检：专项：工具调用结构
Status: Skipped
Samples: 0
跳过原因：service_failure_circuit_breaker
正式来源必检：专项：JSON Schema 结构化输出

按CPA 官方产品源确定的方法执行。执行 专项题，用于形成模真真验真证据。 前序检测已确认源站连接中断，为避免继续制造无效请求，本项已跳过。

Skipped
Test evidence
Check: 正式来源必检：专项：JSON Schema 结构化输出
Status: Skipped
Samples: 0
跳过原因：service_failure_circuit_breaker
Specialty test: token cache usage over 5 rounds

执行 专项题，用于形成模真真验真证据。 检测过程中确认服务类故障，剩余样本和后续检测项已熔断跳过。

Failed
Test evidence
Check: Specialty test: token cache usage over 5 rounds
Status: Failed
Samples: 1
Test type: Text test
Specialty: Token cache usage test (may affect real billing)
Results: Passed 0 / Needs review 0 / Failed 1
Specialty test: 32K context capability

32K 长度样本未形成稳定结果，本次按边界样本记录。

Failed
Test evidence
Check: Specialty test: 32K context capability
Status: Failed
Samples: 1
Test type: Text test
Specialty: Context test
Context tier: 32K
Results: Passed 0 / Needs review 0 / Failed 1

Latest user reviews

No public reviews

Be the first to leave a review.

Comments and feedback on this report

Rating
5 points
Upload images/video