← All comparisons

Gemma 4 26B A4B (Reasoning) vs Claude 3.5 Sonnet (Oct '24)

Google vs Anthropic — side-by-side benchmark comparison

Gemma 4 26B A4B (Reasoning)Claude 3.5 Sonnet (Oct '24)
Intelligence Index31.215.9
Coding Index22.430.2
Math Index
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.20$6.56
Time to first token (s)0.00s0.00s
aime15.7%
aime 25
artificial analysis coding index22.4030.20
artificial analysis intelligence index31.2015.90
artificial analysis math index
gpqa79.2%59.9%
hle18.3%3.9%
ifbench72.4%
lcr55.7%
livecodebench38.1%
math 50077.1%
mmlu pro77.2%
scicode40.0%36.6%
tau243.6%
terminalbench hard13.6%

Benchmark data from Artificial Analysis.