Back

LG AI Research

EXAONE 4.5 33B

ReasoningOpen weights
Intelligence
13.2
Rank 341 of 744 measured models
Coding
23.6
Rank 207 of 298 measured models
Context window
262K
Rank 458 of 1199 measured models

EXAONE 4.5 33B (Reasoning) scores 13.2 on the Artificial Analysis Intelligence Index, ranking 341st of 744 measured models. The closest models on this index are DeepSeek R1 0528 (May '25) (13.1), Qwen3.5 4B (13.1), and GPT-5 nano (13.0).

Artificial Analysis Indices
Reasoning
Intelligence13.2
Rank 341 of 744 measured models
Coding23.6
Rank 207 of 298 measured models
Standard Benchmarks
GPQA Diamond79.4%
Rank 211 of 619 measured models
HLE12.9%
Rank 284 of 664 measured models
IFBench58.0%
Rank 136 of 450 measured models
AA-LCR54.7%
Rank 307 of 575 measured models
TerminalBench Hard20.5%
Rank 173 of 432 measured models
Terminal-Bench 2.121.3%
Rank 177 of 244 measured models
τ²-Bench78.1%
Rank 139 of 440 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