Gemma 2 27B
Zero-eval
#1ARC-E
#1BoolQ
#1Natural Questions
+4 more
by Google
+
+
+
+
About
Gemma 2 27B was developed as an open-source language model with 27 billion parameters, designed to provide researchers and developers with a capable, instruction-tuned model for experimentation and deployment. Built to democratize access to advanced language understanding, it combines strong performance with the flexibility of open-source licensing.
+
+
+
+
Timeline
AnnouncedJun 27, 2024
ReleasedJun 27, 2024
+
+
+
+
Specifications
Training Tokens13.0T
+
+
+
+
License & Family
License
Gemma
Performance Overview
Performance metrics and category breakdown
Overall Performance
16 benchmarks
Average Score
69.1%
Best Score
88.6%
High Performers (80%+)
6+
+
+
+
All Benchmark Results for Gemma 2 27B
Complete list of benchmark scores with detailed information
| ARC-E | text | 0.89 | 88.6% | Self-reported | |
| HellaSwag | text | 0.86 | 86.4% | Self-reported | |
| BoolQ | text | 0.85 | 84.8% | Self-reported | |
| TriviaQA | text | 0.84 | 83.7% | Self-reported | |
| Winogrande | text | 0.84 | 83.7% | Self-reported | |
| PIQA | text | 0.83 | 83.2% | Self-reported | |
| MMLU | text | 0.75 | 75.2% | Self-reported | |
| BIG-Bench | text | 0.75 | 74.9% | Self-reported | |
| GSM8k | text | 0.74 | 74.0% | Self-reported | |
| ARC-C | text | 0.71 | 71.4% | Self-reported |
Showing 1 to 10 of 16 benchmarks
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+