Exaone 4.0 1.2B (Non-reasoning) — benchmark results
Provider: LG AI. Released 2025-07-15. Access: Open.
Unified ELO 1350 ± 28, rank #1412 of 1776 rated models, from 36 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Humanity's Last Exam | 5.84 | Accuracy (%) | 42.9 |
| AA LiveCodeBench | 29.31 | Pass@1 (%) | 34.1 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| AA CritPt | 0 | Accuracy (%) | 27.1 |
| AA AIME 2025 | 24 | Accuracy (%) | 25.7 |
| AA Omniscience - Software Engineering (SWE) - Julia | 4 | Accuracy (%) | 23.7 |
| AA TAU-2 Bench | 20.47 | Accuracy (%) | 19.4 |
| AA GPQA Diamond | 42.42 | Accuracy (%) | 19.2 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 8 | Accuracy (%) | 15.1 |
| AA MMLU-Pro | 50.05 | Accuracy (%) | 14.8 |
| AA Omniscience - Software Engineering (SWE) - Dart | 8 | Accuracy (%) | 9 |
| AA-LCR | 0 | Score (self-reported) | 8.9 |
Interactive version: theaggregate.ai/model?slug=exaone-4-0-1-2b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.