K-EXAONE 2.0: benchmark results
Provider: LG AI. Released 2026-07-31. Access: Open.
Unified ELO 1581 ± 1, rank #510 of 1761 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience | -6.6 | Score | 76.2 |
| AA GPQA Diamond | 82.93 | Accuracy (%) | 72.4 |
| AA Humanity's Last Exam | 18.58 | Accuracy (%) | 70.1 |
| Artificial Analysis Intelligence Index | 23.15 | Intelligence Index | 69.7 |
| BenchmarkList ECI | 125.33 | Capability Index (ECI) | 68 |
| AA CritPt | 0.86 | Accuracy (%) | 62.5 |
| AA Long Context Reasoning | 60 | Accuracy (%) | 54.9 |
| AA GDPval | 923.34 | ELO | 43.9 |
| AA Omniscience - Science, Engineering & Mathematics | 23.9 | Accuracy (%) | 33.6 |
| Tau3 Banking | 11.55 | Success Rate (%) | 33.2 |
| AA-LCR | 57.67 | Accuracy (self-reported) | 26.1 |
| AA Omniscience - Business | 12 | Accuracy (%) | 23.4 |
Interactive version: theaggregate.ai/model?slug=k-exaone-2-0 · How It Works · Data refreshed daily, snapshot 2026-09-05.