K-EXAONE (Reasoning)+1 tiers
K-EXAONE (Reasoning) is developed by LG AI Research, released 2025-12-31.
Also written as: K EXAONE (Reasoning)
Reasoning-effort tiers merged. This page shows the
highest-intelligence tier. It merges 2 tiers of the same model:
K-EXAONE (Reasoning), K-EXAONE (Non-reasoning).
Input price
—
Output price
—
Blended price
—
Intelligence
14.4
64th percentile of 554 models with an Intelligence score
Coding
32.1
46th percentile of 194 models with a Coding score
Math
90.3
Speed
—
Time to first token
—
No API price is published for this model in our data source, so we show
— rather than guess. It may be unreleased via API, open-weights only, or simply not tracked yet.
See all of LG AI Research's models on its provider page, or browse the full model directory.