Back

LG AI Research

EXAONE 4.0 32B

Open weights
Intelligence
6.3
Rank 620 of 744 measured models
Context window
131K
Rank 738 of 1199 measured models

EXAONE 4.0 32B (Non-reasoning) scores 6.3 on the Artificial Analysis Intelligence Index, ranking 620th of 744 measured models. The closest models on this index are Celeris-1 (6.3), Grok-1 (6.3), and Phi-4 Mini Instruct (6.3).

Artificial Analysis Indices
Non-reasoning
Intelligence6.3
Rank 620 of 744 measured models
Math39.3
Rank 160 of 270 measured models
Standard Benchmarks
MMLU Pro76.8%
Rank 158 of 349 measured models
GPQA Diamond62.8%
Rank 386 of 619 measured models
HLE5.0%
Rank 478 of 664 measured models
LiveCodeBench47.2%
Rank 158 of 343 measured models
MATH-50093.9%
Rank 51 of 202 measured models
AIME 202447.0%
Rank 64 of 194 measured models
AIME 202539.3%
Rank 160 of 270 measured models
IFBench33.5%
Rank 347 of 450 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