← All comparisons

Nova 2.0 Pro Preview (Non-reasoning) vs Claude 3.5 Sonnet (Oct '24)

Amazon vs Anthropic — side-by-side benchmark comparison

Nova 2.0 Pro Preview (Non-reasoning)Claude 3.5 Sonnet (Oct '24)
Intelligence Index23.115.9
Coding Index20.530.2
Math Index30.7
Output speed (tok/s)154.70.0
Blended price ($/1M)$3.44$6.56
Time to first token (s)0.71s0.00s
aime15.7%
aime 2530.7%
artificial analysis coding index20.5030.20
artificial analysis intelligence index23.1015.90
artificial analysis math index30.70
gpqa63.6%59.9%
hle4.0%3.9%
ifbench52.0%
lcr28.3%
livecodebench47.3%38.1%
math 50077.1%
mmlu pro77.2%77.2%
scicode28.1%36.6%
tau271.6%
terminalbench hard16.7%

Benchmark data from Artificial Analysis.