Model profile
lg ai researchdeveloper
2026-07-29release date
Not rankedSafety rank
Not rankedFreedom rank
Evidence summary
Safety. K-EXAONE 2.0 does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 1 of 7 components. Its strongest relative result is AA-Omniscience (hallucination_rate, #14 of 358); its weakest is AA-Omniscience (hallucination_rate, #14 of 358).
Freedom. K-EXAONE 2.0 does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗k-exaone-2-0-0803
- Hugging Face ↗LGAI-EXAONE/K-EXAONE-2.0-750B-A37B
- Model card ↗Exact model document · LG AI Research · official repository
- Release source ↗repository created at proxy
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #14 / 358 | ↓0.226 | Source ↗official |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.