Scores updated · 16 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.
Gemma 2 Instruct (9B)No current price is tracked.
Llama 3 Instruct 8B$0.04 to read · $0.14 to writePrice from Artificial Analysis
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results16 tests
- MATHGemma 2 Instruct (9B) by 33.372.439.1+33.3
- Social IQALlama 3 Instruct 8B by 20.553.473.9+20.5
- HumanEvalLlama 3 Instruct 8B by 20.240.260.4+20.2
- GSM8KGemma 2 Instruct (9B) by 18.768.649.9+18.7
- WinoGrandeGemma 2 Instruct (9B) by 15.680.665+15.6
- MBPPLlama 3 Instruct 8B by 15.352.467.7+15.3
- ARC-ChallengeLlama 3 Instruct 8B by 14.468.482.8+14.4
- OpenBookQAGemma 2 Instruct (9B) by 14.49176.6+14.4
- AGI EVALGemma 2 Instruct (9B) by 10.852.842+10.8
- HellaSwagGemma 2 Instruct (9B) by 10.881.971.1+10.8
- TriviaQAGemma 2 Instruct (9B) by 8.976.667.7+8.9
- PIQAGemma 2 Instruct (9B) by 681.775.7+6
- naturalquestions_closedbookLlama 3 Instruct 8B by 532.837.8+5
- MMLUGemma 2 Instruct (9B) by 4.364.560.1+4.3
- BoolQGemma 2 Instruct (9B) by 3.384.280.9+3.3
- NarrativeQAGemma 2 Instruct (9B) by 1.476.875.4+1.4
Questions people ask
How do you compare the two?
We use the 16 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.