← All comparisons

Claude 4.5 Haiku (Non-reasoning) vs Motif-2-12.7B-Reasoning

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

Claude 4.5 Haiku (Non-reasoning)Motif-2-12.7B-Reasoning
Intelligence Index31.019.1
Coding Index29.611.9
Math Index39.080.3
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%80.3%
artificial analysis coding index29.6011.90
artificial analysis intelligence index31.0019.10
artificial analysis math index39.0080.30
gpqa64.6%69.5%
hle4.3%8.2%
ifbench42.0%57.0%
lcr43.7%13.0%
livecodebench51.1%65.1%
math 500
mmlu pro80.0%79.6%
scicode34.4%28.2%
tau232.5%46.5%
terminalbench hard27.3%3.8%

Benchmark data from Artificial Analysis.