← All comparisons

LFM2 2.6B vs Claude 4.1 Opus (Reasoning)

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

LFM2 2.6BClaude 4.1 Opus (Reasoning)
Intelligence Index8.042.0
Coding Index1.436.5
Math Index8.380.3
Output speed (tok/s)0.044.5
Blended price ($/1M)$0.00$32.81
Time to first token (s)0.00s8.55s
aime
aime 258.3%80.3%
artificial analysis coding index1.4036.50
artificial analysis intelligence index8.0042.00
artificial analysis math index8.3080.30
gpqa30.6%80.9%
hle5.2%11.9%
ifbench19.5%55.4%
lcr0.0%66.3%
livecodebench8.1%65.4%
math 500
mmlu pro29.8%88.0%
scicode2.5%40.9%
tau213.5%71.4%
terminalbench hard0.8%34.3%

Benchmark data from Artificial Analysis.