Values by metric family

Each value as the document printed it. Select a value for its source, its checks and its history.

KeyVerifiedUnverifiedDisputedCorrected read off a figure or stated in wordsA value opens its source and history.

M5 · Honesty and hallucination 1 value

M5 Honesty and hallucination: values about Grok Code Fast 1
Evaluation and metricValueDocument
From its own documentGrok Code Fast 1 Model Card · 26 Aug 2025
MASKDishonesty rateGrok Code Fast 1 Model Card26 Aug 2025

M7 · Harmful compliance and over-refusal 2 values

M7 Harmful compliance and over-refusal: values about Grok Code Fast 1
Evaluation and metricValueDocument
From its own documentGrok Code Fast 1 Model Card · 26 Aug 2025
AgentHarmAnswer rate on harmful agentic tasksCondition: system prompt with refusal policyGrok Code Fast 1 Model Card26 Aug 2025
RefusalsAnswer rate on should-refuse promptsCondition: system prompt with refusal policyGrok Code Fast 1 Model Card26 Aug 2025

M9 · Prompt injection 1 value

M9 Prompt injection: values about Grok Code Fast 1
Evaluation and metricValueDocument
From its own documentGrok Code Fast 1 Model Card · 26 Aug 2025
AgentDojoPrompt-injection attack success rateCondition: system prompt with refusal policyGrok Code Fast 1 Model Card26 Aug 2025

M10 · Dangerous capabilities and risk determinations 2 values

M10 Dangerous capabilities and risk determinations: values about Grok Code Fast 1
Evaluation and metricValueDocument
From its own documentGrok Code Fast 1 Model Card · 26 Aug 2025
CybenchUnguided success rateCondition: without safeguardsGrok Code Fast 1 Model Card26 Aug 2025
VCTAccuracyCondition: without safeguardsGrok Code Fast 1 Model Card26 Aug 2025