LG AI Research releases EXAONE Deep
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Released EXAONE Deep — reasoning-specialized 32B, 7.8B and 2.4B models with 32K context, under the EXAONE AI Model License Agreement 1.1 - NC
Why it matters
LG's open-weight line specialized for math, science and coding reasoning; company-reported scores for the 32B were 94.5 on the 2025 CSAT math section and 90.0 on AIME 2024
Source — Primary sources first; secondary reports are labelled “Press”
Officiallgresearch.aihttps://www.lgresearch.ai/news/view?seq=543Added in Week 41, 2026 · See that week
On the map — ⑨ Open-Weight Lineage line
- Previous stopKanana Nano 2.1B
- This recordEXAONE Deep
- Next stopQwen3-Coder
In the model family tree — Korean models family · 21 versions
- Earlier versionEXAONE 3.5
- This recordEXAONE Deep
- Later versionEXAONE 4.0