← All comparisons

Claude 4.5 Haiku (Non-reasoning) vs Exaone 4.0 1.2B (Reasoning)

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

Claude 4.5 Haiku (Non-reasoning)Exaone 4.0 1.2B (Reasoning)
Intelligence Index31.08.3
Coding Index29.63.1
Math Index39.050.3
Output speed (tok/s)105.80.0
Blended price ($/1M)$2.19$0.00
Time to first token (s)0.65s0.00s
aime
aime 2539.0%50.3%
artificial analysis coding index29.603.10
artificial analysis intelligence index31.008.30
artificial analysis math index39.0050.30
gpqa64.6%51.5%
hle4.3%5.8%
ifbench42.0%23.0%
lcr43.7%0.0%
livecodebench51.1%51.6%
math 500
mmlu pro80.0%58.8%
scicode34.4%9.3%
tau232.5%16.4%
terminalbench hard27.3%0.0%

Benchmark data from Artificial Analysis.