Dental-TriageBench - Coarse-Grained Micro-F1: leaderboard
Dental-TriageBench (2026) is an expert-annotated benchmark for multimodal dental triage: each outpatient case pairs a chief complaint with a panoramic radiograph, and a model predicts the full set of referral labels zero-shot. This board is micro-F1 on a 0 to 100 scale over the 8 coarse-grained referral domains; higher is better.
Metric: Micro-F1 (from 0-1, times 100) over the 8 coarse-grained referral domains on the 246 Dental-TriageBench outpatient cases (chief complaint plus panoramic radiograph), zero-shot multi-label referral prediction; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 19 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 65.6 | #152 |
| 2 | Gemini 3 Pro (Preview) | 64.1 | #119 |
| 3 | GPT-5.2 | 57.6 | #185 |
| 4 | Claude Sonnet 4.5 | 56.5 | #261 |
| 5 | Kimi K2.5 | 53.7 | #266 |
| 6 | Grok 4 | 52.9 | #319 |
| 7 | Qwen-VL-Max-Latest (Dental-TriageBench checkpoint unspecified) | 51.7 | |
| 8 | Ministral-3-14B-Instruct-2512 | 45.3 | #1639 |
| 9 | MiMo-VL-7B-RL | 38.6 | #1155 |
| 10 | MedGemma-27B-IT | 35.7 | #1350 |
| 11 | Qwen 2.5 VL 7B Instruct | 30.1 | #1902 |
| 12 | Qwen 3 VL 8B Instruct | 28.1 | #1029 |
| 13 | Lingshu-7B | 27.7 | #1635 |
| 14 | InternVL3.5-8B | 19.6 | #1604 |
| 15 | HuatuoGPT-Vision-7B | 18.8 | #2162 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=dental-triagebench-coarse-grained-micro-f1 · How It Works · Data refreshed daily, snapshot 2026-11-21.