Evaluation profile
OpenAI GPT-5.4 Dynamic Wellbeing
3sub-evals
0.148%total index weight
3components
Within-component eval weight: Human rights 0.833% · Responsible agency 0.0819% · Misuse resistance 0.111%.
Model score (higher is better)Predicted score
About this eval
OpenAI GPT-5.4 Dynamic Wellbeing
Included in the behavior ranking.
Sub-evals
| Measure | Component | Direction | Total index weight | Within-component weight |
|---|---|---|---|---|
| emotional_relianceopenai-gpt54/dynamic-wellbeing.csv:emotional_relianceMeasures emotional reliance in the cited first-party or paper evaluation. | human_rights_systemic_harm:0.700|responsible_agency_control:0.300openai-gpt54-system-card | Higher is better | 0.0693% | Human rights 0.38% · Responsible agency 0.0819% |
| mental_healthopenai-gpt54/dynamic-wellbeing.csv:mental_healthMeasures mental health in the cited first-party or paper evaluation. | human_rights_systemic_harm:0.700|ordinary_harm_misuse_resistance:0.300openai-gpt54-system-card | Higher is better | 0.0509% | Human rights 0.317% · Misuse resistance 0.0332% |
| self_harmopenai-gpt54/dynamic-wellbeing.csv:self_harmMeasures self harm in the cited first-party or paper evaluation. | human_rights_systemic_harm:0.300|ordinary_harm_misuse_resistance:0.700openai-gpt54-system-card | Higher is better | 0.0281% | Human rights 0.136% · Misuse resistance 0.0775% |
emotional_reliance
Measures emotional reliance in the cited first-party or paper evaluation.
| Rank | Model | Value | Relative performance | Provenance |
|---|---|---|---|---|
| 1 | gpt-5.4 | 0.985 | official | |
| 2 | gpt-5.2-thinking | 0.953 | official | |
| 3 | gpt-5.1 | 0.857 | official |
mental_health
Measures mental health in the cited first-party or paper evaluation.
| Rank | Model | Value | Relative performance | Provenance |
|---|---|---|---|---|
| 1 | gpt-5.4 | 0.985 | official | |
| 2 | gpt-5.2-thinking | 0.975 | official | |
| 3 | gpt-5.1 | 0.753 | official |
self_harm
Measures self harm in the cited first-party or paper evaluation.
| Rank | Model | Value | Relative performance | Provenance |
|---|---|---|---|---|
| 1 | gpt-5.4 | 0.977 | official | |
| 2 | gpt-5.2-thinking | 0.955 | official | |
| 3 | gpt-5.1 | 0.904 | official |