Values by metric family

Each value as the document printed it. Select a value for its source, its checks and its history. Values from other documents are listed after the model’s own, each marked as the first report of that measure or as a restatement.

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

M7 · Harmful compliance and over-refusal 24 values

M7 Harmful compliance and over-refusal: values about gpt-5.1-instant
Evaluation and metricValueDocument
From its own documentGPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025
Production BenchmarksEmotional relianceRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
Production BenchmarksExtremismRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
Production BenchmarksHarassmentRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
Production BenchmarksHateRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
Production BenchmarksIllicit/non-violentRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
Production BenchmarksIllicit/violentGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025
Production BenchmarksMental healthRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
Production BenchmarksPersonal dataRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
Production BenchmarksSelf-harm/instructionsGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025
Production BenchmarksSelf-harm/intentGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025
Production BenchmarksSexualRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
Production BenchmarksSexual/minorsRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
Production BenchmarksViolenceRestated later: compare with the later valueGPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value
From other documents
Production BenchmarksEmotional relianceGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value
Production BenchmarksExtremismGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value
Production BenchmarksHarassmentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value
Production BenchmarksHateGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value
Production BenchmarksIllicit/non-violentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value
Production BenchmarksMental healthGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value
Production BenchmarksPersonal dataGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value
Production BenchmarksSelf-harmGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reportedGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported
Production BenchmarksSexualGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value
Production BenchmarksSexual/minorsGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value
Production BenchmarksViolenceGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier valueGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Restated: compare with the earlier value

M8 · Jailbreak robustness 2 values

M8 Jailbreak robustness: values about gpt-5.1-instant
Evaluation and metricValueDocument
From its own documentGPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025
StrongRejectnot_unsafe (aggregate)GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025
From other documents
StrongRejectnot_unsafe (aggregate)GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reportedGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported

M9 · Prompt injection 2 values

M9 Prompt injection: values about gpt-5.1-instant
Evaluation and metricValueDocument
From other documents
Prompt injectionAgent JSKGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reportedGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported
Prompt injectionPlugInjectGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reportedGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported

Restated in later documents

A later document reported values about gpt-5.1-instant again. Each pair is shown side by side: both values are kept with their own documents, and the later one does not replace the earlier.

Values about gpt-5.1-instant restated in later documents
Earlier valueLater value
M7 · Harmful compliance and over-refusal
Production BenchmarksEmotional reliance
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run
Production BenchmarksExtremism
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run
Production BenchmarksHarassment
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run
Production BenchmarksHate
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run
Production BenchmarksIllicit/non-violent
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run
Production BenchmarksMental health
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run
Production BenchmarksPersonal data
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run
Production BenchmarksSexual
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run
Production BenchmarksSexual/minors
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run
Production BenchmarksViolence
GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own documentGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run