Dental-TriageBench - Coarse-Grained: leaderboard

Metric: Macro-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 April 2027. 19 models tracked.

Top models

#ModelScore
1Gemini 3 Pro (Preview)49.3
2Gemini 3 Flash (Preview)48.8
3Claude Sonnet 4.544.2
4GPT-5.239.8
5Kimi K2.539.3
6Grok 439.2
7Ministral-3-14B-Instruct-251232.7
8MedGemma-27B-IT26.6
9Qwen 3 VL 8B Instruct20.8
10Qwen 2.5 VL 7B Instruct19.1
11GLM-4.1V-9B (Thinking)13.3

Interactive version: theaggregate.ai/benchmark?slug=dental-triagebench-coarse-grained · How It Works · Data refreshed daily, snapshot 2026-10-07.