U2-BENCH Leaderboard

A comprehensive benchmark for evaluating large vision-language models on ultrasound understanding tasks. Track the performance of state-of-the-art multimodal models across various ultrasound analysis challenges.

Models Rank U2-Score ↑ DD
Acc ↑
DD
F1 ↑
VRA
Acc ↑
VRA
F1 ↑
LL
Acc ↑
OD
Acc ↑
KD
Acc ↑
CVE
RMSE ↓
CVE
MAE ↓
CVE
%_tol ↑
RG
BLEU% ↑
RG
Rouge% ↑
RG
BERT% ↑
CG
BLEU% ↑
CG
Rouge% ↑
CG
BERT% ↑

Total Models

-

Best Score

-

Last Updated

-