K-EXAONE (Non-reasoning): benchmark results
K-EXAONE evaluated with reasoning disabled. Provider: LG AI. Released 2025-12-31. Access: Open.
Aggregate Rating 1491 ± 17, rank #1132 of 2201 rated models, from 52 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA MMLU-Pro | 80.98 | Accuracy (%) | 73 |
| AA Omniscience - Software Engineering (SWE) - Rust | 50 | Accuracy (%) | 59 |
| Tau2-Bench Telecom | 59.06 | Success Rate (%) | 57.9 |
| AA TAU-2 Bench | 59.06 | Accuracy (%) | 56.3 |
| AA Omniscience - Software Engineering (SWE) - R | 10 | Accuracy (%) | 53.4 |
| AA Omniscience - Software Engineering (SWE) - Swift | 32 | Accuracy (%) | 51.2 |
| AA GPQA Diamond | 69.49 | Accuracy (%) | 47.2 |
| AA AIME 2025 | 44 | Accuracy (%) | 44.3 |
| AA Long Context Reasoning | 53.33 | Accuracy (%) | 44 |
| AA Omniscience - Software Engineering (SWE) - Python | 16 | Accuracy (%) | 43 |
| AA Omniscience - Software Engineering (SWE) - Go | 14 | Accuracy (%) | 41.1 |
| Korean CSAT 2026 (Easy Mode) - Physics I | 26 | Points (out of 50) | 40 |
Interactive version: theaggregate.ai/model?slug=k-exaone-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-12.