MTVQA
Multilingual
multimodal
+
+
+
+
About
MTVQA (Multilingual Text-Centric Visual Question Answering) is the first benchmark featuring high-quality human expert annotations across 9 diverse languages, consisting of 6,778 question-answer pairs across 2,116 images. It addresses visual-textual misalignment problems in multilingual settings, evaluating models' ability to understand text within images across different languages and cultural contexts.
+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
1 models
Top Score
30.9%
Average Score
30.9%
High Performers (80%+)
0Top Organizations
#1Alibaba Cloud / Qwen Team
1 model
30.9%
+
+
+
+
Leaderboard
1 models ranked by performance on MTVQA
| License | Links | ||||
|---|---|---|---|---|---|
| Aug 29, 2024 | tongyi-qianwen | 30.9% |
