← All comparisons

Granite 4.0 H Small vs Claude 4.1 Opus (Reasoning)

IBM vs Anthropic — side-by-side benchmark comparison

Granite 4.0 H SmallClaude 4.1 Opus (Reasoning)
Intelligence Index10.842.0
Coding Index8.536.5
Math Index13.780.3
Output speed (tok/s)401.244.5
Blended price ($/1M)$0.11$32.81
Time to first token (s)8.75s8.55s
aime
aime 2513.7%80.3%
artificial analysis coding index8.5036.50
artificial analysis intelligence index10.8042.00
artificial analysis math index13.7080.30
gpqa41.6%80.9%
hle3.7%11.9%
ifbench31.5%55.4%
lcr9.0%66.3%
livecodebench25.1%65.4%
math 500
mmlu pro62.4%88.0%
scicode20.9%40.9%
tau217.3%71.4%
terminalbench hard2.3%34.3%

Benchmark data from Artificial Analysis.