← All comparisons

Gemini 2.5 Flash Preview (Sep '25) (Reasoning) vs Claude 4.5 Sonnet (Reasoning)

Google vs Anthropic — side-by-side benchmark comparison

Gemini 2.5 Flash Preview (Sep '25) (Reasoning)Claude 4.5 Sonnet (Reasoning)
Intelligence Index31.143.0
Coding Index24.638.6
Math Index78.388.0
Output speed (tok/s)0.055.0
Blended price ($/1M)$0.00$6.56
Time to first token (s)0.00s7.02s
aime
aime 2578.3%88.0%
artificial analysis coding index24.6038.60
artificial analysis intelligence index31.1043.00
artificial analysis math index78.3088.00
gpqa79.3%83.4%
hle12.7%17.3%
ifbench52.3%57.3%
lcr64.3%65.7%
livecodebench71.3%71.4%
math 500
mmlu pro84.2%87.5%
scicode40.5%44.7%
tau245.6%78.1%
terminalbench hard16.7%35.6%

Benchmark data from Artificial Analysis.