Scores updated · 10 tests both models report · How we compare
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Llama 3.3 70B Instruct$0.71 to read · $0.72 to writePrice from Artificial Analysis
Phi 3 Medium 4K InstructNo current price is tracked.
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
- MGSMLlama 3.3 70B Instruct by 37.691.153.5+37.6
- DROPLlama 3.3 70B Instruct by 21.990.268.3+21.9
- HumanEvalLlama 3.3 70B Instruct by 20.688.467.8+20.6
- MMLULlama 3.3 70B Instruct by 18.58667.5+18.5
- MATHLlama 3.3 70B Instruct by 15.97761.1+15.9
- naturalquestions_closedbookLlama 3.3 70B Instruct by 15.343.127.8+15.3
- SimpleQALlama 3.3 70B Instruct by 13.320.97.6+13.3
- NarrativeQALlama 3.3 70B Instruct by 6.779.172.4+6.7
- GSM8KLlama 3.3 70B Instruct by 6.494.287.8+6.4
- OpenBookQALlama 3.3 70B Instruct by 1.292.891.6+1.2
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.