← All comparisons

Exaone 4.0 1.2B (Non-reasoning) vs Claude 4.1 Opus (Reasoning)

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

Exaone 4.0 1.2B (Non-reasoning)Claude 4.1 Opus (Reasoning)
Intelligence Index8.142.0
Coding Index2.536.5
Math Index24.080.3
Output speed (tok/s)0.044.5
Blended price ($/1M)$0.00$32.81
Time to first token (s)0.00s8.55s
aime
aime 2524.0%80.3%
artificial analysis coding index2.5036.50
artificial analysis intelligence index8.1042.00
artificial analysis math index24.0080.30
gpqa42.4%80.9%
hle5.8%11.9%
ifbench25.3%55.4%
lcr0.0%66.3%
livecodebench29.3%65.4%
math 500
mmlu pro50.0%88.0%
scicode7.4%40.9%
tau220.5%71.4%
terminalbench hard0.0%34.3%

Benchmark data from Artificial Analysis.