← All comparisons

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

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

K2-V2 (medium)Claude 4.1 Opus (Non-reasoning)
Intelligence Index18.736.0
Coding Index14.0
Math Index64.7
Output speed (tok/s)0.044.7
Blended price ($/1M)$0.00$32.81
Time to first token (s)0.00s1.63s
aime
aime 2564.7%
artificial analysis coding index14.00
artificial analysis intelligence index18.7036.00
artificial analysis math index64.70
gpqa59.8%
hle4.4%
ifbench55.1%
lcr28.0%
livecodebench54.1%
math 500
mmlu pro76.1%
scicode25.2%
tau224.9%
terminalbench hard8.3%

Benchmark data from Artificial Analysis.