Back

LG AI Research

K-EXAONE

ReasoningOpen weights
Intelligence
14.4
Rank 319 of 744 measured models
Coding
32.1
Rank 178 of 298 measured models
Context window
2.02M
Rank 6 of 1199 measured models

K-EXAONE (Reasoning) scores 14.4 on the Artificial Analysis Intelligence Index, ranking 319th of 744 measured models. The closest models on this index are DeepSeek V3.2 Speciale (14.5), Gemini 2.5 Pro Preview (May' 25) (14.5), and ERNIE 5.0 Thinking Preview (14.3).

Artificial Analysis Indices
Reasoning
Intelligence14.4
Rank 319 of 744 measured models
Coding32.1
Rank 178 of 298 measured models
Math90.3
Rank 25 of 270 measured models
Standard Benchmarks
MMLU Pro83.8%
Rank 45 of 349 measured models
GPQA Diamond78.3%
Rank 225 of 619 measured models
HLE13.9%
Rank 269 of 664 measured models
LiveCodeBench76.8%
Rank 41 of 343 measured models
AIME 202590.3%
Rank 25 of 270 measured models
IFBench64.7%
Rank 107 of 450 measured models
AA-LCR61.3%
Rank 278 of 575 measured models
TerminalBench Hard22.7%
Rank 161 of 432 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy