granite-3.1-1B-a400m-instruct: benchmark results
Provider: IBM. Released 2024-12-18. Access: Open.
Aggregate Rating 1192 ± 30, rank #9656 of 10916 rated models, from 83 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 46.86 | Score | 53.5 |
| Open Japanese LLM - Wiki Coreference SET F1 | 2.33 | Score (%) | 47.4 |
| Open PL LLM - CBD (multiple choice, 5-shot) | 19.29 | Macro F1 (%) | 37.3 |
| Open PL LLM - PSC (multiple choice, 5-shot) | 46.79 | Binary F1 (%) | 34.8 |
| Open PL LLM - EQ-Bench | 16.71 | EQ-Bench Score | 33.8 |
| Open Japanese LLM - Xlsum JA Rouge1 | 20.86 | Score (%) | 29.8 |
| Open Japanese LLM - Wiki NER SET F1 | 1.77 | Score (%) | 27 |
| Open LLM Leaderboard - MATH Level 5 | 4.53 | Score | 25.6 |
| Open Japanese LLM - Xlsum JA RougeLsum | 16.91 | Score (%) | 24.9 |
| Open PL LLM - PSC (generative, 5-shot) | 74.64 | Binary F1 (%) | 23.6 |
| Open PL LLM - PPC (multiple choice, 5-shot) | 47.4 | Accuracy (%) | 21.5 |
| Open Japanese LLM - SUM | 6.32 | Score (%) | 21.4 |
Interactive version: theaggregate.ai/model?slug=granite-3-1-1b-a400m-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.