← All comparisons

Claude 4.5 Haiku (Non-reasoning) vs Gemma 3 1B Instruct

Anthropic vs Google — side-by-side benchmark comparison

Claude 4.5 Haiku (Non-reasoning)Gemma 3 1B Instruct
Intelligence Index31.05.6
Coding Index29.60.2
Math Index39.03.3
Output speed (tok/s)105.80.0
Blended price ($/1M)$2.19$0.00
Time to first token (s)0.65s0.00s
aime0.0%
aime 2539.0%3.3%
artificial analysis coding index29.6020.0%
artificial analysis intelligence index31.005.60
artificial analysis math index39.003.30
gpqa64.6%23.7%
hle4.3%5.2%
ifbench42.0%19.9%
lcr43.7%0.0%
livecodebench51.1%1.7%
math 50048.4%
mmlu pro80.0%13.5%
scicode34.4%0.7%
tau232.5%10.5%
terminalbench hard27.3%0.0%

Benchmark data from Artificial Analysis.