granite-8B-code-base 4K: benchmark results
Provider: IBM. Released 2024-05-06. Access: Open.
Aggregate Rating 1360 ± 37, rank #7451 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Portuguese NLU - HAREM | 49.33 | Micro F1 excluding MISC (%) | 75.5 |
| EuroEval Dutch NLU - CoNLL NL | 63.93 | Micro F1 excluding MISC (%) | 74.3 |
| EuroEval Italian NLU - MultiNERD IT | 67.3 | Micro F1 excluding MISC (%) | 66.5 |
| EuroEval Norwegian NLU - NorNE NB | 68.77 | Micro F1 excluding MISC (%) | 65.3 |
| EuroEval French NLU - Eltec | 59.47 | Micro F1 excluding MISC (%) | 64.2 |
| EuroEval Faroese NLU - FONE | 66.86 | Micro F1 excluding MISC (%) | 62.7 |
| EuroEval Swedish NLU - SUC3 | 60.37 | Micro F1 excluding MISC (%) | 61.9 |
| EuroEval Spanish NLU - MLQA ES | 61.53 | Character F1 (%) | 60.1 |
| EuroEval Icelandic NLU - MIM-GOLD NER | 51.13 | Micro F1 excluding MISC (%) | 58.3 |
| EuroEval Norwegian NLU - NorNE NN | 63.89 | Micro F1 excluding MISC (%) | 56.3 |
| EuroEval Spanish NLU - CoNLL ES | 62.24 | Micro F1 excluding MISC (%) | 55.9 |
| EuroEval German NLU - GermEval | 57.96 | Micro F1 excluding MISC (%) | 51.9 |
Interactive version: theaggregate.ai/model?slug=granite-8b-code-base-4k · How It Works · Data refreshed daily, snapshot 2026-11-08.