Scores updated · 10 tests both models report · How we compare
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results10 tests
- MGSMGemini 1.5 Pro by 3487.553.5+34
- MATHGemini 1.5 Pro by 21.482.561.1+21.4
- naturalquestions_closedbookGemini 1.5 Pro by 17.845.527.8+17.8
- HumanEvalGemini 1.5 Pro by 16.384.167.8+16.3
- SimpleQAGemini 1.5 Pro by 15.823.47.6+15.8
- MMLUGemini 1.5 Pro by 1279.567.5+12
- DROPGemini 1.5 Pro by 6.674.968.3+6.6
- OpenBookQAGemini 1.5 Pro by 3.695.291.6+3.6
- NarrativeQAGemini 1.5 Pro by 3.275.672.4+3.2
- GSM8KGemini 1.5 Pro by 390.887.8+3
Questions people ask
How do you compare the two?
We use the 10 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.