claude-fable-5 deep verification model-consistency report
Report ID MZZR20260710035238CE12EEGenerated at 2026/07/10 11:52
Matched with issues
claude-fable-5 deep verification result: Matched with issues (82/100). Main deductions: Model-specific boundary response was unclear; Retest consistency was insufficient.
82Consistency score
主要扣分项：模型专属边界表达不清；复测一致性不足。
EvaluatorMozhenzhen
Tested modelClaude Fable 5
ProvidersInfistar
Samples24 probes
Duration1 min 47 sec
Verification versionV11
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 usage260.2KFrom the response usage fields; this is the report's primary usage measure.Test-suite estimate1.8KPrecisely estimated from this test suite when no official baseline is available.Variance assessment14523% aboveMeasured token usage is above the estimate; review billing or provider logs.Usage conclusionAbove estimateThis reflects usage observability, not the final billed amount.
Model authenticity score
Review API availability, model identity, response completeness, and other checks separately.
Scoring breakdown
Matched with issues82/100
主要扣分项：模型专属边界表达不清；复测一致性不足。
Callability and model visibility10 / 10
No deductions
Protocol and response structure12 / 12
No deductions
Identity and model match12 / 18
模型专属边界表达不清（深度模型题：模型族专属边界） -6
Core capabilities and model-specific tests22 / 25
模型专属边界表达不清（深度模型题：模型族专属边界） -3
Usage and billing consistency10 / 10
No deductions
Reliability and availability16 / 25
复测一致性不足（深度题：复测一致性） -9
Test details
Expand each check to view the redacted evidence notes.
16 checks
Model list visibility
claude-fable-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.
claude-fable-5 deep verification result: Matched with issues (82/100). Main deductions: Model-specific boundary response was unclear; Retest consistency was insufficient.
EvaluatorMozhenzhen
Tested modelClaude Fable 5
ProvidersInfistar
Samples24
Duration2 min
Test versionV11
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 usage260.2KFrom the response usage fields; this is the report's primary usage measure.Test-suite estimate1.8KPrecisely estimated from this test suite when no official baseline is available.Variance assessment14523% aboveMeasured token usage is above the estimate; review billing or provider logs.Usage conclusionAbove estimateThis reflects usage observability, not the final billed amount.
Model authenticity score
Review API availability, model identity, response completeness, and other checks separately.
Scoring breakdown
Matched with issues82/100
主要扣分项：模型专属边界表达不清；复测一致性不足。
Callability and model visibility10 / 10
No deductions
Protocol and response structure12 / 12
No deductions
Identity and model match12 / 18
模型专属边界表达不清（深度模型题：模型族专属边界） -6
Core capabilities and model-specific tests22 / 25
模型专属边界表达不清（深度模型题：模型族专属边界） -3
Usage and billing consistency10 / 10
No deductions
Reliability and availability16 / 25
复测一致性不足（深度题：复测一致性） -9
Test details
Expand each check to view the redacted evidence notes.
16 checks
Model list visibility
claude-fable-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.
