← All comparisons

Granite 4.0 350M vs Claude 3.5 Sonnet (June '24)

IBM vs Anthropic — side-by-side benchmark comparison

Granite 4.0 350MClaude 3.5 Sonnet (June '24)
Intelligence Index6.114.2
Coding Index0.326.0
Math Index0.0
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$6.56
Time to first token (s)0.00s0.00s
aime9.7%
aime 250.0%
artificial analysis coding index30.0%26.00
artificial analysis intelligence index6.1014.20
artificial analysis math index0.0%
gpqa26.1%56.0%
hle5.7%3.7%
ifbench15.9%
lcr0.0%
livecodebench2.4%
math 50069.5%
mmlu pro12.4%75.1%
scicode0.9%31.6%
tau213.2%
terminalbench hard0.0%

Benchmark data from Artificial Analysis.