Scores updated · 11 tests both models report · How we compare
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results11 tests
- HumanEvalKimi K2 Base by 30.178.248.1+30.1
- MMLU-ProKimi K2 Base by 26.869.242.4+26.8
- MBPPKimi K2 Base by 25.28963.8+25.2
- MATHKimi K2 Base by 24.970.245.3+24.9
- BBHKimi K2 Base by 23.588.765.2+23.5
- TriviaQAKimi K2 Base by 18.885.166.3+18.8
- MMLUKimi K2 Base by 17.887.870+17.8
- C-EvalKimi K2 Base by 15.392.577.2+15.3
- GSM8KKimi K2 Base by 14.792.177.4+14.7
- CMMLUKimi K2 Base by 12.790.978.2+12.7
- CMathKimi K2 Base by 9.790.881.1+9.7
Questions people ask
How do you compare the two?
We use the 11 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.