← All comparisons

Granite 4.1 3B vs Claude 3.5 Haiku

IBM vs Anthropic — side-by-side benchmark comparison

Granite 4.1 3BClaude 3.5 Haiku
Intelligence Index8.518.7
Coding Index5.510.7
Math Index
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$1.75
Time to first token (s)0.00s0.00s
aime3.3%
aime 25
artificial analysis coding index5.5010.70
artificial analysis intelligence index8.5018.70
artificial analysis math index
gpqa31.4%40.8%
hle3.4%3.5%
ifbench33.7%42.8%
lcr3.0%23.3%
livecodebench31.4%
math 50072.1%
mmlu pro63.4%
scicode11.9%27.4%
tau219.6%24.6%
terminalbench hard2.3%2.3%

Benchmark data from Artificial Analysis.