granite-3.0-8B-base: benchmark results
IBM's Apache-2.0 Granite 3.0 8B base model (October 2024), pretrained on 12T tokens in two stages as the foundation for the enterprise instruct variant. Provider: IBM. Released 2024-10-21. Access: Open.
Aggregate Rating 1414 ± 25, rank #5488 of 10916 rated models, from 99 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Dutch NLU - SQuAD NL | 78.32 | Character F1 (%) | 88 |
| EuroEval German NLU - Sb10K | 57.84 | Matthews correlation coefficient (%) | 86.8 |
| EuroEval Italian NLU - SQuAD IT | 72.62 | Character F1 (%) | 86.2 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 75.27 | Character F1 (%) | 85.9 |
| EuroEval German NLU - Germanquad | 61.9 | Character F1 (%) | 83.1 |
| EuroEval Spanish NLU - MLQA ES | 65.01 | Character F1 (%) | 82.9 |
| EuroEval Portuguese NLU - SST-2 PT | 82.81 | Matthews correlation coefficient (%) | 80.7 |
| Open LLM Leaderboard - GPQA | 32.55 | Score | 78.5 |
| EuroEval Dutch | 65.53 | Average Score (%) | 78.2 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 46.12 | Matthews correlation coefficient (%) | 73.1 |
| EuroEval English NLU - SST-5 | 66.89 | Matthews correlation coefficient (%) | 68.3 |
| EuroEval Spanish NLU - ScaLA ES | 25.47 | Matthews correlation coefficient (%) | 65.7 |
Interactive version: theaggregate.ai/model?slug=granite-3-0-8b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.