Scores updated · 5 tests both models report · How we compare
Every test, side by side
All 5 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results5 tests
- AGIEval 5-shotQwen3 14B Base by 6.566.159.6+6.5
- TriviaQA 5-shotQwen3 14B Base by 6.470.363.9+6.4
- Multilingual MMLUQwen3 14B Base by 5.475.470+5.4
- MMLUQwen3 14B Base by 4.480.476+4.4
- MMLU Redux 5-shotQwen3 14B Base by 4.383.779.4+4.3
Questions people ask
How do you compare the two?
We use the 5 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.