Granite 4.0 H Tiny: benchmark results

Provider: IBM. Released 2025-10-02. Access: Open.

Aggregate Rating 1407 ± 17, rank #5937 of 10552 rated models, from 324 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Enkrypt AI - Toxicity Risk0.36Risk Score92.3
LatamBoard - Spanish TeleIA71.43Score (%)86.4
LatamBoard - Spanish MGSM12.8Score (%)81.8
LatamBoard - Spanish Score62.42Score (%)81.8
LatamBoard - Translation Score44.15Score (%)78.8
LatamBoard - FLORES Bidirectional42.71Score (%)75.8
LatamBoard - Spanish OpenBookQA36.4Score (%)75.8
LatamBoard68.75LatamBoard Category Average (percentage)74.4
EuroEval Swedish NLU - Swerec77.27Matthews correlation coefficient (%)74.3
EuroEval Hungarian NLU - HuSST52.81Matthews correlation coefficient (%)73.5
LatamBoard - Spanish Escola70.37Score (%)72.7
EuroEval Catalan NLU - Guia CAT62.7Matthews correlation coefficient (%)68.2

Interactive version: theaggregate.ai/model?slug=granite-4-0-h-tiny · How It Works · Data refreshed daily, snapshot 2026-11-16.