Dental Panoramic X-ray Interpretation on OPG-Bench
49.7Overall ScoreOPGAgent
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OPGAgent2026.02 | 49.7 | 43.1 | 41.5 | 42.3 | 4.89 | 71.5 | 45.6 | 55.7 | 62.5 | 37.6 | 46.9 | 80.1 | |
| Gemini-3-Flash2026.02 | 42.8 | 27.6 | 45.1 | 34.3 | 10.58 | 44 | 59.6 | 50.6 | 31.1 | 48.8 | 38 | 79.6 | |
| Kimi-k2.52026.02 | 39.9 | 25.2 | 34.5 | 29.1 | 9.2 | 48.1 | 50 | 49 | 34.8 | 46.3 | 39.7 | 76.4 | |
| Gemini-3-Pro2026.02 | 39.9 | 32.3 | 29.4 | 30.8 | 5.6 | 55.6 | 43.1 | 48.5 | 45.8 | 31.9 | 37.6 | 73.2 | |
| GPT-5.22026.02 | 35.7 | 28.3 | 27.3 | 27.8 | 6.17 | 62.4 | 35.9 | 45.6 | 39.2 | 19.3 | 25.8 | 75.4 | |
| DentalGPT2026.02 | 29.5 | 12.8 | 20 | 15.6 | 12.22 | 46.4 | 48.3 | 47.3 | 24.1 | 27.3 | 25.6 | 71.5 | |
| MedAgent-Pro2026.02 | 27.8 | 17.1 | 18.3 | 17.7 | 8 | 41.2 | 43.8 | 42.5 | 20.6 | 20.4 | 20.5 | 63.2 | |
| Qwen3-VL-235B2026.02 | 23 | 10.6 | 19.1 | 13.7 | 14.5 | 31.6 | 43.6 | 36.6 | 10.7 | 17.5 | 13.3 | 61.4 | |
| Qwen3-VL-8B2026.02 | 19.7 | 10.2 | 7 | 8.3 | 5.5 | 40.9 | 25.9 | 31.7 | 17.5 | 12.4 | 14.5 | 63.5 | |
| OralGPT-Omni2026.02 | 15.7 | 9.4 | 4.6 | 6.2 | 4.02 | 45.7 | 15.1 | 22.7 | 14.5 | 7.5 | 9.9 | 60.3 |