← All comparisons

Gemini 2.5 Flash-Lite (Non-reasoning) vs Claude 4.1 Opus (Reasoning)

Google vs Anthropic — side-by-side benchmark comparison

Gemini 2.5 Flash-Lite (Non-reasoning)Claude 4.1 Opus (Reasoning)
Intelligence Index12.742.0
Coding Index7.436.5
Math Index35.380.3
Output speed (tok/s)294.244.5
Blended price ($/1M)$0.17$32.81
Time to first token (s)0.34s8.55s
aime50.0%
aime 2535.3%80.3%
artificial analysis coding index7.4036.50
artificial analysis intelligence index12.7042.00
artificial analysis math index35.3080.30
gpqa47.4%80.9%
hle3.7%11.9%
ifbench31.5%55.4%
lcr31.3%66.3%
livecodebench40.0%65.4%
math 50092.6%
mmlu pro72.4%88.0%
scicode17.7%40.9%
tau219.0%71.4%
terminalbench hard2.3%34.3%

Benchmark data from Artificial Analysis.