MTBBench-Multimodal: leaderboard
Metric: Accuracy (%; unweighted mean of the three task accuracies; 26 head-and-neck cancer patients from HANCOCK, 390 true/false and six-option multiple-choice questions; multi-turn agent that requests patient files, no tools). Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL3-78B | 69.1 |
| 2 | GPT-4o (2024-08-06) | 66.7 |
| 3 | O4 Mini (2025-04-16) | 64.3 |
| 4 | InternVL3-38B | 63.5 |
Interactive version: theaggregate.ai/benchmark?slug=mtbbench-multimodal · How It Works · Data refreshed daily, snapshot 2026-09-26.