Back

LG AI Research

Exaone 4.0 1.2B

ReasoningOpen weights
Intelligence
5.3
Rank 687 of 744 measured models
Context window
64K
Rank 995 of 1199 measured models

Exaone 4.0 1.2B (Reasoning) scores 5.3 on the Artificial Analysis Intelligence Index, ranking 687th of 744 measured models. The closest models on this index are Command-R+ (Apr '24) (5.3), DBRX Instruct (5.3), and DeepSeek Coder V2 Lite Instruct (5.3).

Artificial Analysis Indices
Reasoning
Intelligence5.3
Rank 687 of 744 measured models
Math50.3
Rank 140 of 270 measured models
Standard Benchmarks
MMLU Pro58.8%
Rank 271 of 349 measured models
GPQA Diamond51.5%
Rank 463 of 619 measured models
HLE6.0%
Rank 428 of 664 measured models
LiveCodeBench51.6%
Rank 143 of 343 measured models
AIME 202550.3%
Rank 140 of 270 measured models
IFBench23.0%
Rank 426 of 450 measured models
AA-LCR0.0%
Rank 513 of 575 measured models
TerminalBench Hard0.0%
Rank 385 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