← All comparisons

EXAONE 4.5 33B (Non-reasoning) vs Claude 3 Haiku

LG AI Research vs Anthropic — side-by-side benchmark comparison

EXAONE 4.5 33B (Non-reasoning)Claude 3 Haiku
Intelligence Index12.3
Coding Index6.7
Math Index
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$0.50
Time to first token (s)0.00s0.00s
aime1.0%
aime 25
artificial analysis coding index6.70
artificial analysis intelligence index12.30
artificial analysis math index
gpqa37.4%
hle3.9%
ifbench36.1%
lcr21.0%
livecodebench15.4%
math 50039.4%
mmlu pro
scicode18.6%
tau221.1%
terminalbench hard0.8%

Benchmark data from Artificial Analysis.