← All comparisons

LFM2 8B A1B vs Claude 4.1 Opus (Non-reasoning)

Liquid AI vs Anthropic — side-by-side benchmark comparison

LFM2 8B A1BClaude 4.1 Opus (Non-reasoning)
Intelligence Index7.036.0
Coding Index2.3
Math Index25.3
Output speed (tok/s)0.044.7
Blended price ($/1M)$0.00$32.81
Time to first token (s)0.00s1.63s
aime
aime 2525.3%
artificial analysis coding index2.30
artificial analysis intelligence index7.0036.00
artificial analysis math index25.30
gpqa34.4%
hle4.9%
ifbench26.3%
lcr0.0%
livecodebench15.1%
math 500
mmlu pro50.5%
scicode6.8%
tau210.5%
terminalbench hard0.0%

Benchmark data from Artificial Analysis.