← All comparisons

Gemma 4 26B A4B (Non-reasoning) vs Claude 3.5 Sonnet (June '24)

Google vs Anthropic — side-by-side benchmark comparison

Gemma 4 26B A4B (Non-reasoning)Claude 3.5 Sonnet (June '24)
Intelligence Index27.114.2
Coding Index29.126.0
Math Index
Output speed (tok/s)71.10.0
Blended price ($/1M)$0.20$6.56
Time to first token (s)0.80s0.00s
aime9.7%
aime 25
artificial analysis coding index29.1026.00
artificial analysis intelligence index27.1014.20
artificial analysis math index
gpqa71.4%56.0%
hle10.7%3.7%
ifbench45.4%
lcr39.7%
livecodebench
math 50069.5%
mmlu pro75.1%
scicode37.3%31.6%
tau240.4%
terminalbench hard25.0%

Benchmark data from Artificial Analysis.