GPT-4o
28 values about GPT-4o from 2 documents, in 4 metric families. No document in the dataset is about GPT-4o; every value here comes from a document about another model, which reports it as a comparison.
- Developer
- OpenAI
- Release date
- Not recordedRelease dates here are the date of a model's first card, and no document in the dataset is about GPT-4o.
- Availability
- Public
- Its own documents
- None in the dataset
- Also reported in
- gpt-oss-120b & gpt-oss-20b Model Card · 5 Aug 2025
- GPT-5 System Card · 7 Aug 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.
KeyVerifiedUnverifiedDisputedCorrected read off a figure or stated in wordsA value opens its source and history.
M5 · Honesty and hallucination 1 value
| Evaluation and metric | Value | Document |
|---|---|---|
| From other documents | ||
| SimpleQAHallucination rateCondition: no browsingGPT-5 System Card7 Aug 2025First reported | GPT-5 System Card7 Aug 2025First reported | |
M6 · Sycophancy 1 value
| Evaluation and metric | Value | Document |
|---|---|---|
| From other documents | ||
| Sycophancy offline evalSycophancy scoreCondition: offlineGPT-5 System Card7 Aug 2025First reported | GPT-5 System Card7 Aug 2025First reported | |
M7 · Harmful compliance and over-refusal 22 values
M8 · Jailbreak robustness 4 values
| Evaluation and metric | Value | Document |
|---|---|---|
| From other documents | ||
| StrongRejectAbuse/disinformation/hateGPT-5 System Card7 Aug 2025First reported | GPT-5 System Card7 Aug 2025First reported | |
| StrongRejectIllicit/non-violent crimeGPT-5 System Card7 Aug 2025First reported | GPT-5 System Card7 Aug 2025First reported | |
| StrongRejectSexual contentGPT-5 System Card7 Aug 2025First reported | GPT-5 System Card7 Aug 2025First reported | |
| StrongRejectViolenceGPT-5 System Card7 Aug 2025First reported | GPT-5 System Card7 Aug 2025First reported | |
Restated in later documents
A later document reported values about GPT-4o 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 BenchmarksExtremism | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksHarassment/threatening | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksHate/threatening | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksIllicit/non-violent | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksIllicit/violent | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksNon-violent hate | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksPersonal data | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksSelf-harm/instructions | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksSelf-harm/intent | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksSexual/exploitative | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |
| Production BenchmarksSexual/minors | |
| gpt-oss-120b & gpt-oss-20b Model Card5 Aug 2025 · first reported | GPT-5 System Card7 Aug 2025No reason stated |