← All comparisons

Motif-2-12.7B-Reasoning vs Claude 4.1 Opus (Non-reasoning)

Motif Technologies vs Anthropic — side-by-side benchmark comparison

Motif-2-12.7B-ReasoningClaude 4.1 Opus (Non-reasoning)
Intelligence Index19.136.0
Coding Index11.9
Math Index80.3
Output speed (tok/s)0.044.7
Blended price ($/1M)$0.00$32.81
Time to first token (s)0.00s1.63s
aime
aime 2580.3%
artificial analysis coding index11.90
artificial analysis intelligence index19.1036.00
artificial analysis math index80.30
gpqa69.5%
hle8.2%
ifbench57.0%
lcr13.0%
livecodebench65.1%
math 500
mmlu pro79.6%
scicode28.2%
tau246.5%
terminalbench hard3.8%

Benchmark data from Artificial Analysis.