K-EXAONE

by LG AI Research

Released · 169 days after EXAONE 4.0 32B

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Intelligence Index (previous version)14.4
Coding
LiveCodeBench
77%
Agentic & knowledge work
GDPval
0%
Terminal-Bench Hard
23%
τ²-Bench Telecom
74%
Science & reasoning
Humanity's Last Exam
14%
GPQA Diamond
78%
Long-context reasoning
61%
Knowledge
MMLU-Pro
84%
Math & instruction following
AIME 2025
90%
IFBench
65%

Available routes

No routes currently available — K-EXAONE isn't routed through the Opper gateway right now. It's tracked here for its release history.

Contact us about this model →

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation