Granite 3.3 8B (Non-reasoning) — benchmark results

Provider: IBM. Released 2025-02-26. Access: Open.

Unified ELO 1305 ± 31, rank #1520 of 1776 rated models, from 37 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA Omniscience - Software Engineering (SWE) - R6Accuracy (%)30.9
CritPt0Accuracy (self-reported)30.3
AA CritPt0Accuracy (%)27.1
AA MATH-50066.47Accuracy (%)24.8
AA Omniscience - Software Engineering (SWE) - Go10Accuracy (%)24.7
AA Omniscience - Software Engineering (SWE) - TypeScript11.11Accuracy (%)22.8
AA Omniscience - Software Engineering (SWE) - PHP14Accuracy (%)22.5
AA-LCR4.3Score (self-reported)20.9
AA Omniscience - Software Engineering (SWE) - Python11Accuracy (%)19.9
AA Omniscience - Software Engineering (SWE) - C21Accuracy (%)18.4
AA Omniscience - Software Engineering (SWE) - HTML18Accuracy (%)17.5
AA Humanity's Last Exam4.22Accuracy (%)16.2

Interactive version: theaggregate.ai/model?slug=granite-3-3-8b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.