granite-3.1-3B-a800m-base: benchmark results
Provider: IBM. Access: Open.
Unified ELO 1286 ± 24, rank #1484 of 1632 rated models, from 95 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - PSC (multiple choice, 5-shot) | 46.7 | Binary F1 (%) | 34.5 |
| Open PL LLM - EQ-Bench | 16.57 | EQ-Bench Score | 33.4 |
| Open LLM Leaderboard - GPQA | 27.77 | Score | 32.7 |
| Open LLM Leaderboard - IFEval | 29.96 | Score | 27.3 |
| Open Japanese LLM - Wiki NER SET F1 | 1.77 | Score (%) | 27 |
| BhashaBench - Ayur - English | 31.75 | Accuracy (%) | 26.7 |
| BhashaBench - Krishi - English | 33.36 | Accuracy (%) | 26.7 |
| Open PL LLM - KLEJ NER (generative, 5-shot) | 36.15 | Accuracy (%) | 26.4 |
| Open LLM Leaderboard - MATH Level 5 | 4.53 | Score | 25.8 |
| Open Japanese LLM - Xlsum JA Rouge1 | 19.33 | Score (%) | 24.8 |
| Open Japanese LLM - Jemhopqa Char F1 | 42.42 | Score (%) | 24.3 |
| Open Japanese LLM - SUM | 6.92 | Score (%) | 23.8 |
Interactive version: theaggregate.ai/model?slug=granite-3-1-3b-a800m-base · How It Works · Data refreshed daily, snapshot 2026-10-08.