← All comparisons

K2-V2 (low) vs Claude 4.1 Opus (Non-reasoning)

MBZUAI Institute of Foundation Models vs Anthropic — side-by-side benchmark comparison

K2-V2 (low)Claude 4.1 Opus (Non-reasoning)
Intelligence Index14.436.0
Coding Index10.5
Math Index35.3
Output speed (tok/s)0.044.7
Blended price ($/1M)$0.00$32.81
Time to first token (s)0.00s1.63s
aime
aime 2535.3%
artificial analysis coding index10.50
artificial analysis intelligence index14.4036.00
artificial analysis math index35.30
gpqa54.1%
hle3.9%
ifbench41.0%
lcr19.0%
livecodebench39.3%
math 500
mmlu pro71.3%
scicode22.3%
tau220.8%
terminalbench hard4.5%

Benchmark data from Artificial Analysis.