Granite 3.3 8B Base
Multimodal
Zero-eval
#1AttaQ
#1AlpacaEval 2.0
#1NQ
+2 more
by IBM
+
+
+
+
About
Granite 3.3 8B Base was developed by IBM as an enterprise-focused foundation model, designed to provide a reliable starting point for business applications. Built with 8 billion parameters and trained on curated data, it serves as a foundation for domain-specific customization in enterprise contexts.
+
+
+
+
Timeline
AnnouncedApr 16, 2025
ReleasedApr 16, 2025
Knowledge CutoffApr 1, 2024
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Apache 2.0
Performance Overview
Performance metrics and category breakdown
Overall Performance
20 benchmarks
Average Score
64.3%
Best Score
89.7%
High Performers (80%+)
5+
+
+
+
All Benchmark Results for Granite 3.3 8B Base
Complete list of benchmark scores with detailed information
| HumanEval | text | 0.90 | 89.7% | Self-reported | |
| AttaQ | text | 0.89 | 88.5% | Self-reported | |
| HumanEval+ | text | 0.86 | 86.1% | Self-reported | |
| AIME 2024 | text | 0.81 | 81.2% | Self-reported | |
| HellaSwag | text | 0.80 | 80.1% | Self-reported | |
| TriviaQA | text | 0.78 | 78.2% | Self-reported | |
| IFEval | text | 0.75 | 74.8% | Self-reported | |
| Winogrande | text | 0.74 | 74.4% | Self-reported | |
| BIG-Bench Hard | text | 0.69 | 69.1% | Self-reported | |
| MATH-500 | text | 0.69 | 69.0% | Self-reported |
Showing 1 to 10 of 20 benchmarks
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+