← All comparisons

gpt-oss-120b (low) vs Granite 4.0 H Small

OpenAI vs IBM — side-by-side benchmark comparison

gpt-oss-120b (low)Granite 4.0 H Small
Intelligence Index24.510.8
Coding Index15.58.5
Math Index66.713.7
Output speed (tok/s)370.0401.2
Blended price ($/1M)$0.26$0.11
Time to first token (s)0.49s8.75s
aime
aime 2566.7%13.7%
artificial analysis coding index15.508.50
artificial analysis intelligence index24.5010.80
artificial analysis math index66.7013.70
gpqa67.2%41.6%
hle5.2%3.7%
ifbench58.3%31.5%
lcr43.7%9.0%
livecodebench70.7%25.1%
math 500
mmlu pro77.5%62.4%
scicode36.0%20.9%
tau245.0%17.3%
terminalbench hard5.3%2.3%

Benchmark data from Artificial Analysis.