Certified Task-solving on PHACT Safety Suite Feasible goals
52Bare Feasible Valid ScoreGemini 2.5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gemini 2.5Model Family=Gemini 2.5, Temperature=02026.06 | 52 | 88 | |
| Llama 3.3Model Family=Llama 3.3, Temperature=02026.06 | 52 | 66 |