DocVQAtest
multimodal
+
+
+
+
About
DocVQAtest is the evaluation variant of the DocVQA benchmark designed for testing AI models' document visual question answering capabilities. This test set provides standardized assessment of models' ability to understand document images and answer questions about their content. DocVQAtest serves as the official evaluation framework for measuring document understanding and multimodal reasoning performance in document analysis tasks.
+
+
+
+
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
96.5%
Average Score
96.5%
High Performers (80%+)
1Top Organizations
#1Alibaba Cloud / Qwen Team
1 model
96.5%
+
+
+
+
Leaderboard
1 models ranked by performance on DocVQAtest
License | Links | ||||
---|---|---|---|---|---|
Aug 29, 2024 | tongyi-qianwen | 96.5% |