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
- OpenBookQACommand Light by 17.639.822.2+17.6
- GSM8KCommand Light by 10.514.94.4+10.5
- MMLUCommand Light by 8.138.630.5+8.1
- naturalquestions_closedbookOLMo (7B) by 6.419.525.9+6.4
- NarrativeQACommand Light by 3.36359.7+3.3
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.