← All comparisons

Gemma 4 26B A4B (Non-reasoning) vs Claude 4.1 Opus (Reasoning)

Google vs Anthropic — side-by-side benchmark comparison

Gemma 4 26B A4B (Non-reasoning)Claude 4.1 Opus (Reasoning)
Intelligence Index27.142.0
Coding Index29.136.5
Math Index80.3
Output speed (tok/s)71.144.5
Blended price ($/1M)$0.20$32.81
Time to first token (s)0.80s8.55s
aime
aime 2580.3%
artificial analysis coding index29.1036.50
artificial analysis intelligence index27.1042.00
artificial analysis math index80.30
gpqa71.4%80.9%
hle10.7%11.9%
ifbench45.4%55.4%
lcr39.7%66.3%
livecodebench65.4%
math 500
mmlu pro88.0%
scicode37.3%40.9%
tau240.4%71.4%
terminalbench hard25.0%34.3%

Benchmark data from Artificial Analysis.