← All comparisons

K2-V2 (high) vs Claude 3.5 Sonnet (June '24)

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

K2-V2 (high)Claude 3.5 Sonnet (June '24)
Intelligence Index20.614.2
Coding Index16.126.0
Math Index78.3
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$6.56
Time to first token (s)0.00s0.00s
aime9.7%
aime 2578.3%
artificial analysis coding index16.1026.00
artificial analysis intelligence index20.6014.20
artificial analysis math index78.30
gpqa68.1%56.0%
hle9.8%3.7%
ifbench60.1%
lcr33.3%
livecodebench69.4%
math 50069.5%
mmlu pro78.6%75.1%
scicode28.6%31.6%
tau227.8%
terminalbench hard9.8%

Benchmark data from Artificial Analysis.