Exaone 4.0 1.2B (Non-reasoning): benchmark results

Provider: LG AI. Released 2025-07-15. Access: Open.

Unified ELO 1369 ± 1, rank #1826 of 2032 rated models, from 84 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA Omniscience - Software Engineering (SWE) - Julia4.35Accuracy (%)39.4
AA Humanity's Last Exam5.7Accuracy (%)35.5
AA LiveCodeBench29.31Pass@1 (%)34.1
AA Omniscience - Software Engineering (SWE) - Kotlin10.2Accuracy (%)27.8
MERA Industrial - ruTXTMedQFundamental - Histology27.4Score (%)26.7
MERA Industrial - ruTXTMedQFundamental - Pathological anatomy30.7Score (%)26.2
AA AIME 202524Accuracy (%)25.3
MERA Industrial - ruTXTMedQFundamental - General surgery31.9Score (%)23.8
AA CritPt0Accuracy (%)23.2
MERA Industrial - ruTXTMedQFundamental - Biophysics28.5Score (%)22.3
MERA Industrial - ruTXTMedQFundamental - Pharmacology27.4Score (%)22.3
MERA Industrial - ruTXTMedQFundamental - Clinical laboratory diagnostics28.1Score (%)21.8

Interactive version: theaggregate.ai/model?slug=exaone-4-0-1-2b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-26.