K-EXAONE (Reasoning): benchmark results
Provider: LG AI. Released 2025-12-31. Access: Open.
Aggregate Rating 1535 ± 18, rank #962 of 2201 rated models, from 53 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA AIME 2025 | 90.33 | Accuracy (%) | 90.8 |
| AA LiveCodeBench | 76.83 | Pass@1 (%) | 88.3 |
| AA MMLU-Pro | 83.75 | Accuracy (%) | 87.1 |
| AA IFBench | 64.69 | Accuracy (%) | 76.4 |
| LG K-EXAONE 2.0 Card - HRM8K-KSM | 91.9 | Accuracy (%) | 75 |
| LG K-EXAONE 2.0 Card - KGC-Safety | 96.1 | Safe Rate (%) | 75 |
| Tau2-Bench Telecom | 74.27 | Success Rate (%) | 67.4 |
| AA Omniscience - Software Engineering (SWE) - Dart | 22 | Accuracy (%) | 66.2 |
| AA TAU-2 Bench | 74.27 | Accuracy (%) | 66.1 |
| AA GPQA Diamond | 78.28 | Accuracy (%) | 64.1 |
| AA Terminal-Bench Hard | 22.73 | Accuracy (%) | 62.6 |
| AA Global-MMLU-Lite - Korean | 85.17 | Accuracy (%) | 60 |
Interactive version: theaggregate.ai/model?slug=k-exaone-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-12.