Gemma 3n E4B
Multimodal
Zero-eval
#3ARC-E
by Google
+
+
+
+
About
Gemma 3n E4B is a multimodal language model developed by Google. It achieves strong performance with an average score of 64.6% across 11 benchmarks. It excels particularly in ARC-E (81.6%), BoolQ (81.6%), PIQA (81.0%). As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents Google's latest advancement in AI technology.
+
+
+
+
Timeline
AnnouncedJun 26, 2025
ReleasedJun 26, 2025
Knowledge CutoffJun 1, 2024
+
+
+
+
Specifications
Training Tokens11.0T
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
11 benchmarks
Average Score
64.6%
Best Score
81.6%
High Performers (80%+)
3+
+
+
+
All Benchmark Results for Gemma 3n E4B
Complete list of benchmark scores with detailed information
| ARC-E | text | 0.82 | 81.6% | Self-reported | |
| BoolQ | text | 0.82 | 81.6% | Self-reported | |
| PIQA | text | 0.81 | 81.0% | Self-reported | |
| HellaSwag | text | 0.79 | 78.6% | Self-reported | |
| Winogrande | text | 0.72 | 71.7% | Self-reported | |
| TriviaQA | text | 0.70 | 70.2% | Self-reported | |
| ARC-C | text | 0.62 | 61.6% | Self-reported | |
| DROP | text | 0.61 | 60.8% | Self-reported | |
| BIG-Bench Hard | text | 0.53 | 52.9% | Self-reported | |
| Social IQa | text | 0.50 | 50.0% | Self-reported |
Showing 1 to 10 of 11 benchmarks