DentalGPT Dental Eval Suite: leaderboard
Dental multimodal evaluation suite covering panoramic X-ray understanding, filtered dental VQA, intraoral image classification, and panorama classification for dental disease and condition recognition.
Metric: Average Accuracy (imported). Source: github.com. Source: benchmarklist.com. Saturation forecast: Around March 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 59.2 | #98 |
| 2 | Llama 4 Maverick | 58.5 | #464 |
| 3 | GPT-4.1 | 58.3 | #248 |
| 4 | Gemini 2.5 Pro (Thinking) | 57.9 | #152 (Gemini 2.5 Pro) |
| 5 | Grok 4.1 Fast | 56.7 | #217 |
| 6 | Claude Sonnet 4.5 (Thinking) | 56.4 | #142 (Claude Sonnet 4.5) |
| 7 | Qwen 3 VL 235B A22B (Thinking) | 55 | #238 (Qwen 3 VL 235B A22B) |
| 8 | GLM-4.5V | 54.2 | #346 |
| 9 | ERNIE-4.5-VL-424B-A47B | 52.9 | #391 |
| 10 | Phi-4 Multimodal Instruct | 52 | #906 |
| 11 | Claude Sonnet 4.5 | 51.7 | #142 |
| 12 | Gemma 3 27B (IT) | 51.5 | #523 |
| 13 | Qwen 3 VL 235B A22B Instruct | 51.3 | #273 |
| 14 | Mistral Large 3 | 48.6 | #401 |
| 15 | Qwen 2.5 VL 7B Instruct | 46.7 | #654 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=dentalgpt-dental-eval-suite · How It Works · Data refreshed daily, snapshot 2026-10-20.