Grok-1.5V
Multimodal
Zero-eval
#3RealWorldQA
by xAI
+
+
+
+
About
Grok 1.5V was introduced as a vision-enabled variant of Grok 1.5, designed to understand and reason about both images and text. Built to extend Grok's capabilities into multimodal applications, it enables visual question answering and image analysis alongside textual understanding.
+
+
+
+
Timeline
AnnouncedApr 12, 2024
ReleasedApr 12, 2024
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
7 benchmarks
Average Score
71.9%
Best Score
88.3%
High Performers (80%+)
2+
+
+
+
All Benchmark Results for Grok-1.5V
Complete list of benchmark scores with detailed information
| AI2D | multimodal | 0.88 | 88.3% | Self-reported | |
| DocVQA | multimodal | 0.86 | 85.6% | Self-reported | |
| TextVQA | multimodal | 0.78 | 78.1% | Self-reported | |
| ChartQA | multimodal | 0.76 | 76.1% | Self-reported | |
| RealWorldQA | multimodal | 0.69 | 68.7% | Self-reported | |
| MMMU | multimodal | 0.54 | 53.6% | Self-reported | |
| MathVista | multimodal | 0.53 | 52.8% | Self-reported |
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+