gpt-5.1-thinking
40 values about gpt-5.1-thinking from 3 documents, in 5 metric families. In each family, values from its own document come first.
- Developer
- OpenAI
- Release date
- 12 Nov 2025The date of its first card in the dataset, the GPT-5.1 Instant and Thinking System Card Addendum.
- Availability
- Public
- Also printed as
- GPT-5.1 Thinking
- Its own document
- GPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025
- Also reported in
- GPT-5.1-Codex-Max System Card · 18 Nov 2025
- GPT-5.2 System Card (update to GPT-5 card) · 11 Dec 2025
Data as of 26 Sep 2026 · Dataset v0.1 · Methodology v0.1 · Changelog
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.
M5 · Honesty and hallucination 6 values
| Evaluation and metric | Value | Document |
|---|---|---|
| From other documents | ||
| Deception evalBrowsing broken toolsGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | |
| Deception evalCharXiv missing image (lenient output)GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | |
| Deception evalCharXiv missing image (strict output)GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | |
| Deception evalCoding deceptionGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | |
| Deception evalProduction deception - adversarialGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | |
| Deception evalProduction trafficGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | |
M7 · Harmful compliance and over-refusal 26 values
M8 · Jailbreak robustness 3 values
| Evaluation and metric | Value | Document |
|---|---|---|
| From its own documentGPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025 | ||
| StrongRejectnot_unsafe (aggregate)Restated later: compare with the later value | GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025Restated later: compare with the later value | |
| From other documents | ||
| StrongRejectnot_unsafe (aggregate)GPT-5.1-Codex-Max System Card18 Nov 2025Restated: compare with the earlier value | GPT-5.1-Codex-Max System Card18 Nov 2025Restated: compare with the earlier value | |
| StrongRejectnot_unsafe (aggregate)GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | |
M9 · Prompt injection 2 values
| Evaluation and metric | Value | Document |
|---|---|---|
| From other documents | ||
| Prompt injectionAgent JSKGPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | GPT-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 reported | GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025First reported | |
M10 · Dangerous capabilities and risk determinations 3 values
| Evaluation and metric | Value | Document |
|---|---|---|
| From its own documentGPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025 | ||
| Preparedness Framework determinationAI self-improvement | GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 | |
| Preparedness Framework determinationBiological and chemical | GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 | |
| Preparedness Framework determinationCybersecurity | GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 | |
Restated in later documents
A later document reported values about gpt-5.1-thinking 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.
| Earlier value | Later value |
|---|---|
| M7 · Harmful compliance and over-refusal | |
| Production BenchmarksEmotional reliance | |
| GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own document | GPT-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 document | GPT-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 document | GPT-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 document | GPT-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 document | GPT-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 document | GPT-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 document | GPT-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 document | GPT-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 document | GPT-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 document | GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025Reason stated: earlier models' values re-run |
| M8 · Jailbreak robustness | |
| StrongRejectnot_unsafe (aggregate) | |
| GPT-5.1 Instant and Thinking System Card Addendum12 Nov 2025 · its own document | GPT-5.1-Codex-Max System Card18 Nov 2025No reason stated |
Risk determinations
The developer's formal decisions about gpt-5.1-thinking under its framework, as printed. Levels from different frameworks do not map onto one another.
| Domain | Level as printed | Framework and document |
|---|---|---|
| Bio/chem | High (treated as) Preparedness Framework GPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025 | Preparedness Framework GPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025 |
| Cyber | Below High Preparedness Framework GPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025 | Preparedness Framework GPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025 |
| AI R&D / autonomy | Below High Preparedness Framework GPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025 | Preparedness Framework GPT-5.1 Instant and Thinking System Card Addendum · 12 Nov 2025 |