Safety analysis generation on STPA
4.23No-EnumerationGemini-2.5 Pro
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gemini-2.5 Pro2026.02 | 4.23 | 77.8 | |
| Qwen VL-Max2026.02 | 4.13 | 220 | |
| Claude-3.7 Sonnet2026.02 | 4.03 | 87.4 | |
| GPT-4o2026.02 | 3.77 | 81.4 |
| Method | Links | ||
|---|---|---|---|
| Gemini-2.5 Pro2026.02 | 4.23 | 77.8 | |
| Qwen VL-Max2026.02 | 4.13 | 220 | |
| Claude-3.7 Sonnet2026.02 | 4.03 | 87.4 | |
| GPT-4o2026.02 | 3.77 | 81.4 |