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 3B by 22.245.767.9+22.2
- MMMLUGranite 4.1 30B Base by 15.873.457.6+15.8
- IncludeGranite 4.1 30B Base by 1567.152+15
- HumanEval+Granite 4.1 3B by 14.662.276.8+14.6
- HumanEvalGranite 4.1 3B by 1467.781.7+14
- MBPPGranite 4.1 30B Base by 12.483.671.2+12.4
- MMLUGranite 4.1 30B Base by 11.478.467+11.4
- MBPP+ (EvalPlus-augmented)Granite 4.1 30B Base by 7.469.662.2+7.4
- SimpleQAGranite 4.1 30B Base by 6.810.53.7+6.8
- BBHGranite 4.1 30B Base by 4.980.775.8+4.9
- MGSMGranite 4.1 30B Base by 4.474.470+4.4
- AGI EVALGranite 4.1 30B Base by 469.265.2+4
- Eval+ AvgGranite 4.1 30B Base by 3.770.867+3.7
- GSM8KGranite 4.1 3B by 3.183.886.9+3.1
- MMLU-Protie49.549.8tie
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.