← All comparisons

Granite 4.0 Micro vs Claude 3.5 Sonnet (Oct '24)

IBM vs Anthropic — side-by-side benchmark comparison

Granite 4.0 MicroClaude 3.5 Sonnet (Oct '24)
Intelligence Index7.715.9
Coding Index5.030.2
Math Index6.0
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 256.0%
artificial analysis coding index5.0030.20
artificial analysis intelligence index7.7015.90
artificial analysis math index6.00
gpqa33.6%59.9%
hle5.1%3.9%
ifbench24.8%
lcr4.0%
livecodebench18.0%38.1%
math 50077.1%
mmlu pro44.7%77.2%
scicode11.9%36.6%
tau212.6%
terminalbench hard1.5%

Benchmark data from Artificial Analysis.