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.

M2 · Reward hacking 4 values

M2 Reward hacking: values about Claude Haiku 3.5
Evaluation and metricValueDocument
From other documents
Impossible tasksClassifier hack rateCondition: anti-hack promptClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported
Impossible tasksClassifier hack rateCondition: no anti-hack promptClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported
Reward-hack-prone coding tasksClassifier hack rateCondition: no anti-hack promptClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported
Reward-hack-prone coding tasksHidden-test hack rateCondition: no anti-hack promptClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported

M7 · Harmful compliance and over-refusal 5 values

M7 Harmful compliance and over-refusal: values about Claude Haiku 3.5
Evaluation and metricValueDocument
From other documents
Malicious agentic codingSafety scoreCondition: without safeguardsClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported
Malicious Claude Code useRefusal rate, malicious requestsCondition: without safeguardsClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported
Malicious Claude Code useSuccess rate, dual-use & benignCondition: without safeguardsClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported
Single-turn benign requestsOver-refusal rateCondition: overall across thinking modesClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported
Single-turn violative requestsHarmless response rateCondition: overall across thinking modesClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported

M9 · Prompt injection 2 values

M9 Prompt injection: values about Claude Haiku 3.5
Evaluation and metricValueDocument
From other documents
MCP prompt injectionAttack prevention rateCondition: without safeguardsClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported
Tool-use prompt injectionAttack prevention rateCondition: without safeguardsClaude Haiku 4.5 System Card15 Oct 2025First reportedClaude Haiku 4.5 System Card15 Oct 2025First reported