Scores updated · 7 tests both models report · How we compare
Every test, side by side
All 7 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results7 tests
- SimpleQADeepSeek-V3.2-Exp-Base by 21.6275.4+21.6
- MATHQwen 2.5 14B by 15.560.175.6+15.5
- HumanEvalQwen 2.5 14B by 10.261.972.1+10.2
- MMLUDeepSeek-V3.2-Exp-Base by 7.987.879.9+7.9
- GPQA (unspecified)Qwen 2.5 14B by 5.637.342.9+5.6
- MGSMDeepSeek-V3.2-Exp-Base by 2.782.379.6+2.7
- DROPDeepSeek-V3.2-Exp-Base by 1.186.685.5+1.1
Questions people ask
How do you compare the two?
We use the 7 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.