granite-3.0-3B-a800m-instruct — benchmark results

Provider: IBM. Released 2024-10-03. Access: Open.

Unified ELO 1340 ± 24, rank #1437 of 1776 rated models, from 37 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Spanish NLU - MLQA ES62.81Reading comprehension Score (%)68.1
EuroEval Portuguese NLU - SST-2 PT79.46Sentiment classification Score (%)62.7
EuroEval Dutch NLU - DBRD88.43Sentiment classification Score (%)58.7
EuroEval Italian NLU - SQuAD IT65.67Reading comprehension Score (%)49.4
Open LLM Leaderboard - IFEval42.98Score45
EuroEval Spanish NLU - ScaLA ES4.87Linguistic acceptability Score (%)39.3
EuroEval Italian NLU - Sentipolc1644.07Sentiment classification Score (%)37.6
Open LLM Leaderboard - MATH Level 57.02Score37.5
Open LLM Leaderboard - GPQA4.14Score36
EuroEval Spanish NLU36.18NLU Average Score (%)34.4
EuroEval Portuguese NLU - ScaLA PT4.32Linguistic acceptability Score (%)33.4
EuroEval Spanish Common Sense Reasoning19.35Common Sense Reasoning Average Score (%)32.9

Interactive version: theaggregate.ai/model?slug=granite-3-0-3b-a800m-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.