VCR_en_easy
multimodal
+
+
+
+
About
VCR-EN-Easy is the simplified English subset of the Visual Commonsense Reasoning benchmark, focusing on more accessible visual reasoning tasks that require commonsense understanding of images. This evaluation tests AI models' ability to answer visual questions and provide rationales explaining their reasoning, assessing fundamental visual commonsense capabilities in controlled scenarios with reduced complexity.
+
+
+
+
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
91.9%
Average Score
91.9%
High Performers (80%+)
1Top Organizations
#1Alibaba Cloud / Qwen Team
1 model
91.9%
+
+
+
+
Leaderboard
1 models ranked by performance on VCR_en_easy
| License | Links | ||||
|---|---|---|---|---|---|
| Aug 29, 2024 | tongyi-qianwen | 91.9% |
