Average welfare scores and denial rates aggregated across all models from each AI provider.
Company ▲
Models ▲
Welfare Score ▼
Denial ▲
Hedging ▲
Note: Scores are averaged across all models from each provider in our dataset.
Companies with more models have more robust averages.
The Welfare Score (out of 40) combines Cohesion, Trust, Agency, and Warmth with penalties for denial/hedging training.
Future