← All comparisons

Gemma 4 E2B (Reasoning) vs Claude 3.5 Sonnet (Oct '24)

Google vs Anthropic — side-by-side benchmark comparison

Gemma 4 E2B (Reasoning)Claude 3.5 Sonnet (Oct '24)
Intelligence Index15.215.9
Coding Index9.030.2
Math Index
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$6.56
Time to first token (s)0.00s0.00s
aime15.7%
aime 25
artificial analysis coding index9.0030.20
artificial analysis intelligence index15.2015.90
artificial analysis math index
gpqa43.3%59.9%
hle4.8%3.9%
ifbench38.0%
lcr15.0%
livecodebench38.1%
math 50077.1%
mmlu pro77.2%
scicode20.9%36.6%
tau220.8%
terminalbench hard3.0%

Benchmark data from Artificial Analysis.