Llama 3 Instruct 8B is the stronger all-rounder.
Scores updated · 28 tests both models report · How we compare
Where each one wins
Tests won in each of the one area where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Reasoning rests on a single test.
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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Llama 3 Instruct 8B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.9points ahead
Where Gemma (7B) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 28 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningLlama 3 Instruct 8B
- GPQA DiamondLlama 3 Instruct 8B by 3.925.729.6+3.9
Other results27 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- HumanEvalLlama 3 Instruct 8B by 23.237.260.4+23.2
- ARC-ChallengeLlama 3 Instruct 8B by 21.761.182.8+21.7
- TruthfulQALlama 3 Instruct 8B by 18.444.863.2+18.4
- MBPPLlama 3 Instruct 8B by 17.150.667.7+17.1
- BoolQLlama 3 Instruct 8B by 14.96680.9+14.9
- WinoGrandeGemma (7B) by 147965+14
- HellaSwagGemma (7B) by 11.182.271.1+11.1
- MATHGemma (7B) by 10.95039.1+10.9
- MedQALlama 3 Instruct 8B by 10.949.660.5+10.9
- ANLILlama 3 Instruct 8B by 8.648.757.3+8.6
- Social IQALlama 3 Instruct 8B by 8.465.573.9+8.4
- MultiPL-EGemma (7B) by 7.129.722.6+7.1
- GSM8KGemma (7B) by 655.949.9+6
- C-EvalLlama 3 Instruct 8B by 5.943.649.5+5.9
- TriviaQAGemma (7B) by 4.672.367.7+4.6
- naturalquestions_closedbookLlama 3 Instruct 8B by 4.233.637.8+4.2
- OpenBookQAGemma (7B) by 4.280.876.6+4.2
- MMLULlama 3 Instruct 8B by 3.157.160.1+3.1
- Multi-MathematicsGemma (7B) by 2.839.136.3+2.8
- BBHLlama 3 Instruct 8B by 2.655.157.7+2.6
- PIQAGemma (7B) by 2.478.175.7+2.4
- MMLU-ProLlama 3 Instruct 8B by 1.733.735.4+1.7
- EvalPlustie39.640.3tie
- Theorem QAtie21.522.1tie
- Popular aggregated benchmarktie59.459.9tie
- NarrativeQAtie75.275.4tie
- AGI EVALtie42.142tie
Questions people ask
Which is better, Gemma (7B) or Llama 3 Instruct 8B?
Llama 3 Instruct 8B wins the one area where both have results: reasoning. Gemma (7B) wins none.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 1 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 27 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.