K-EXAONE 2.0

by LG AI Research

Released · 125 days after EXAONE 4.5 33B

Benchmarks

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

Intelligence Index7.6
Coding0.5
Agentic1.9
Coding
FrontierCode 2.0
1%
Terminal-Bench 4.0
0%
SciCode
42%
Agentic & knowledge work
AutomationBench
4%
GDPval
16%
GDP.pdf
4%
Briefcase (Elo)651
Science & reasoning
Terminal-Bench Science
0%
CritPt (hard)
4%
HLE Diamond
6%
Humanity's Last Exam
19%
GPQA Diamond
83%
Long-context reasoning
60%
Knowledge
Omniscience-11.5
By domain
Finance & accounting
18.5
Legal
17.1
Engineering
18.2
Economics
18.4
Strategy & operations
10.9

Available routes

No routes currently available — K-EXAONE 2.0 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