← All comparisons

Granite 4.0 1B vs Claude 3.5 Sonnet (Oct '24)

IBM vs Anthropic — side-by-side benchmark comparison

Granite 4.0 1BClaude 3.5 Sonnet (Oct '24)
Intelligence Index7.315.9
Coding Index2.930.2
Math Index6.3
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$6.56
Time to first token (s)0.00s0.00s
aime15.7%
aime 256.3%
artificial analysis coding index2.9030.20
artificial analysis intelligence index7.3015.90
artificial analysis math index6.30
gpqa28.1%59.9%
hle5.1%3.9%
ifbench20.5%
lcr4.0%
livecodebench4.7%38.1%
math 50077.1%
mmlu pro32.5%77.2%
scicode8.7%36.6%
tau222.8%
terminalbench hard0.0%

Benchmark data from Artificial Analysis.