← All comparisons

Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) vs Claude 4.5 Sonnet (Reasoning)

Google vs Anthropic — side-by-side benchmark comparison

Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Claude 4.5 Sonnet (Reasoning)
Intelligence Index19.443.0
Coding Index14.538.6
Math Index46.788.0
Output speed (tok/s)0.055.0
Blended price ($/1M)$0.17$6.56
Time to first token (s)0.00s7.02s
aime
aime 2546.7%88.0%
artificial analysis coding index14.5038.60
artificial analysis intelligence index19.4043.00
artificial analysis math index46.7088.00
gpqa65.1%83.4%
hle4.6%17.3%
ifbench41.8%57.3%
lcr48.0%65.7%
livecodebench64.1%71.4%
math 500
mmlu pro79.6%87.5%
scicode28.5%44.7%
tau230.4%78.1%
terminalbench hard7.6%35.6%

Benchmark data from Artificial Analysis.