← All comparisons

Claude 4.5 Haiku (Reasoning) vs Gemini 3 Flash Preview (Reasoning)

Anthropic vs Google — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)Gemini 3 Flash Preview (Reasoning)
Intelligence Index37.146.4
Coding Index32.642.6
Math Index83.797.0
Output speed (tok/s)142.2192.1
Blended price ($/1M)$2.19$1.13
Time to first token (s)10.48s6.35s
aime
aime 2583.7%97.0%
artificial analysis coding index32.6042.60
artificial analysis intelligence index37.1046.40
artificial analysis math index83.7097.00
gpqa67.2%89.8%
hle9.7%34.7%
ifbench54.3%78.0%
lcr70.3%66.3%
livecodebench61.5%90.8%
math 500
mmlu pro76.0%89.0%
scicode43.3%50.6%
tau254.7%80.4%
terminalbench hard27.3%38.6%

Benchmark data from Artificial Analysis.