← All comparisons

Claude 4.5 Haiku (Reasoning) vs Granite 4.0 H 1B

Anthropic vs IBM — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)Granite 4.0 H 1B
Intelligence Index37.18.0
Coding Index32.62.7
Math Index83.76.3
Output speed (tok/s)142.20.0
Blended price ($/1M)$2.19$0.00
Time to first token (s)10.48s0.00s
aime
aime 2583.7%6.3%
artificial analysis coding index32.602.70
artificial analysis intelligence index37.108.00
artificial analysis math index83.706.30
gpqa67.2%26.3%
hle9.7%5.0%
ifbench54.3%26.2%
lcr70.3%6.3%
livecodebench61.5%11.5%
math 500
mmlu pro76.0%27.7%
scicode43.3%8.2%
tau254.7%19.6%
terminalbench hard27.3%0.0%

Benchmark data from Artificial Analysis.