Scores updated · 16 tests both models report · How we compare
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results16 tests
- MBPPKimi K2 Base by 16.472.689+16.4
- MMLU-ProKimi K2 Base by 960.269.2+9
- HellaSwagKimi K2 Base by 7.886.894.6+7.8
- HumanEvalKimi K2 Base by 6.871.478.2+6.8
- DROPHunyuan Large by 5.388.983.6+5.3
- TriviaQAHunyuan Large by 4.189.285.1+4.1
- PIQAHunyuan Large by 3.488.384.9+3.4
- WinoGrandeHunyuan Large by 3.488.785.3+3.4
- BBHKimi K2 Base by 2.486.388.7+2.4
- ARC-ChallengeKimi K2 Base by 1.29596.2+1.2
- CMMLUtie90.290.9tie
- GSM8Ktie92.892.1tie
- C-Evaltie91.992.5tie
- MMLUtie88.487.8tie
- CMathtie91.390.8tie
- MATHtie69.870.2tie
Questions people ask
How do you compare the two?
We use the 16 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.