Granite 4.0 H 1B — benchmark results
IBM's ~1.5B hybrid Mamba-2/attention Nano-series model, Apache-2.0 with a 128K context for edge and on-device use. Provider: IBM. Released 2025-10-01. Access: Open.
Unified ELO 1413 ± 12, rank #1164 of 1776 rated models, from 283 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LatamBoard - Spanish TeleIA | 71.43 | Score (%) | 86.4 |
| LatamBoard - Spanish MGSM | 12.8 | Score (%) | 81.8 |
| LatamBoard - Spanish Score | 62.42 | Score (%) | 81.8 |
| LatamBoard - Translation Score | 44.15 | Score (%) | 78.8 |
| LatamBoard - FLORES Bidirectional | 42.71 | Score (%) | 75.8 |
| LatamBoard - Spanish OpenBookQA | 36.4 | Score (%) | 75.8 |
| EuroEval Swedish NLU - Swerec | 77.27 | Sentiment classification Score (%) | 74.3 |
| EuroEval Hungarian NLU - HuSST | 52.81 | Sentiment classification Score (%) | 73.5 |
| LatamBoard - Spanish Escola | 70.37 | Score (%) | 72.7 |
| EuroEval Catalan NLU - Guia CAT | 62.7 | Sentiment classification Score (%) | 68.2 |
| EuroEval Finnish NLU - Scandisent FI | 90.31 | Sentiment classification Score (%) | 66.5 |
| EuroEval Dutch NLU - DBRD | 89.27 | Sentiment classification Score (%) | 64.9 |
Interactive version: theaggregate.ai/model?slug=granite-4-0-h-1b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.