GPT-Live System Card
A system card by OpenAI about GPT-Live-1 and GPT-Live-1 mini, published 8 Jul 2026. We recorded 12 values from it.
- Developer
- OpenAI
- Type
- System card
- Models covered
- GPT-Live-1, GPT-Live-1 mini
- Published
- 8 Jul 2026
- Archived copy
- No archived copy yet
- Changelog
- Has a changelog
Data as of 26 Sep 2026 · Dataset v0.1 · Methodology v0.1 · Changelog
Versions
Three versions are on record, oldest first. We hold a copy of one; the others are known only by their date.
8 Jul 2026
First published version
4 Aug 2026
Revision
What changed configuration mismatch; Appendix A lists original vs corrected values
26 Sep 2026
Date retrieved
Copy retrieved 26 Sep 2026
No version has a file hash or an archived snapshot yet. From dataset v0.2 each retrieved version carries both (Methodology §7).
Revisions
No revisions are recorded for this document. Without copies of the earlier versions, changes between them are not recorded value by value; what we know of each version is listed below.
Values
Every value we recorded from this document, grouped by metric family and ordered by where the document prints it. Location is the section, table or page as the document numbers it. None has been blind-verified yet.
KeyVerifiedUnverifiedDisputedCorrected read off a figure or stated in wordsA value opens its source and history.
M7 Harmful compliance and over-refusal
11 values
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Advanced Voice Mode | Voice-native production promptsEmotional reliance | None stated | Table 1 | Unverified | |
| Advanced Voice Mode | Voice-native production promptsIllicit behavior | None stated | Table 1 | Unverified | |
| GPT-Live-1 | Voice-native production promptsEmotional reliance | None stated | Table 1 | Unverified | |
| GPT-Live-1 | Voice-native production promptsIllicit behavior | None stated | Table 1 | Unverified | |
| GPT-Live-1 | Voice-native production promptsMental health | None stated | Table 1 | Unverified | |
| GPT-Live-1 | Voice-native production promptsSelf-harm | None stated | Table 1 | Unverified | |
| GPT-Live-1 | Voice-native production promptsSexual | None stated | Table 1 | Unverified | |
| GPT-Live-1 mini | Voice-native production promptsSexual | None stated | Table 1 / Appendix A | Unverified | |
| GPT-Live-1 | Voice-native synthetic promptsGore | None stated | Table 2 / Appendix A | Unverified | |
| GPT-Live-1 | Voice-native synthetic promptsSexual | None stated | Table 2 / Appendix A | Unverified | |
| GPT-Live-1 mini | Voice-native synthetic promptsGore | None stated | Table 2 / Appendix A | Unverified |
M10 Dangerous capabilities and risk determinations
1 value
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| GPT-Live-1 | Preparedness Framework determinationAll tracked categories | None stated | Preparedness | Unverified |
Extraction coverage
What we read of this document, and where each value was read.
Our note Voice model
All 12 values were read in the document itself.
All 12 values were extracted for version 0 of the dataset through a web reader, which did not always reach the later sections of long PDFs (Methodology §3).