Scores updated · 13 tests both models report · How we compare
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results13 tests
- MMLU-ProKimi K2 Base by 3237.269.2+32
- HumanEval+Kimi K2 Base by 30.554.384.8+30.5
- SimpleQAKimi K2 Base by 28.46.835.3+28.4
- MGSMKimi K2 Base by 26.758.585.2+26.7
- BBHKimi K2 Base by 24.963.888.7+24.9
- IncludeKimi K2 Base by 23.951.875.7+23.9
- MMLUKimi K2 Base by 21.366.587.8+21.3
- MMMLUKimi K2 Base by 2156.677.6+21
- GSM8KKimi K2 Base by 19.272.992.1+19.2
- DROPKimi K2 Base by 17.66683.6+17.6
- MBPPKimi K2 Base by 7.581.589+7.5
- MBPP+ (EvalPlus-augmented)Kimi K2 Base by 5.568.373.8+5.5
- HumanEvalKimi K2 Base by 276.278.2+2
Questions people ask
How do you compare the two?
We use the 13 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.