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
- TriviaQA 5-shotQwen3 8B Base by 10.95363.9+10.9
- MMLUQwen3 8B Base by 4.771.376+4.7
- MMLU Redux 5-shotQwen3 8B Base by 3.575.979.4+3.5
- AGIEval 5-shotQwen3 8B Base by 2.65759.6+2.6
- Multilingual MMLUQwen3 8B Base by 2.367.770+2.3
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.