Damage Recognition on Dataset A
62.7AccuracyGemini-3-Pro
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Gemini-3-ProModel=Gemini-3-Pro2026.06 | 62.7 | 0.19 | |
| ChatGPT-5.1Model=ChatGPT-5.12026.06 | 57.3 | 0.213 | |
| GPT-5-miniModel=GPT-5-mini2026.06 | 38.7 | 0.307 | |
| Gemini-2.5-ProModel=Gemini-2.5-Pro2026.06 | 38 | 0.373 | |
| Gemini-2.5-flashModel=Gemini-2.5-flash2026.06 | 36 | 0.363 |