Scores updated · 15 tests both models report · How we compare
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results15 tests
- Minerva MathGranite 4.1 30B by 37.981.343.4+37.9
- HumanEval+Granite 4.1 30B by 22.685.462.8+22.6
- MBPPGranite 4.1 30B by 21.785.563.8+21.7
- GSM8KGranite 4.1 30B by 20.794.273.5+20.7
- Eval+ AvgGranite 4.1 30B by 20.582.762.2+20.5
- HumanEvalGranite 4.1 30B by 20.188.468.3+20.1
- MBPP+ (EvalPlus-augmented)Granite 4.1 30B by 19.573.554+19.5
- MMLU-ProGranite 4.1 30B by 19.564.144.6+19.5
- AGI EVALGranite 4.1 30B by 16.177.861.7+16.1
- BBHGranite 4.1 30B by 9.983.773.8+9.9
- IncludeGranite 4.1 30B by 9.767.357.6+9.7
- MMMLUGranite 4.1 30B by 973.764.7+9
- MGSMGranite 4.1 30B by 7.471.163.7+7.4
- MMLUGranite 4.1 30B by 6.680.273.6+6.6
- SimpleQAGranite 4.1 8B Base by 1.16.87.9+1.1
Questions people ask
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.