← All comparisons

Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) vs Claude 4.1 Opus (Reasoning)

Google vs Anthropic — side-by-side benchmark comparison

Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Claude 4.1 Opus (Reasoning)
Intelligence Index19.442.0
Coding Index14.536.5
Math Index46.780.3
Output speed (tok/s)0.044.5
Blended price ($/1M)$0.17$32.81
Time to first token (s)0.00s8.55s
aime
aime 2546.7%80.3%
artificial analysis coding index14.5036.50
artificial analysis intelligence index19.4042.00
artificial analysis math index46.7080.30
gpqa65.1%80.9%
hle4.6%11.9%
ifbench41.8%55.4%
lcr48.0%66.3%
livecodebench64.1%65.4%
math 500
mmlu pro79.6%88.0%
scicode28.5%40.9%
tau230.4%71.4%
terminalbench hard7.6%34.3%

Benchmark data from Artificial Analysis.