Scores updated · 3 tests both models report · How we compare
Every test, side by side
All 3 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results3 tests
- MMLU-ReduxDeepSeek-V2 by 16.277.961.7+16.2
- MMLU-ProDeepSeek-V2 by 14.651.436.8+14.6
- MultiPL-EDeepSeek-V2 by 844.436.4+8
Questions people ask
How do you compare the two?
We use the 3 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.