Llama 3 Instruct 8B vs Phi 3 Mini 4K Instruct
Wins 1 of 4 areas
Coding
Wins 2 of 4 areas
Reasoning · Long documents
Phi 3 Mini 4K Instruct wins more areas, narrowly.Llama 3 Instruct 8B is better at coding.
Scores updated · 26 tests both models report · How we compare
Where each one wins
Tests won in each of the four areas 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.
- ReasoningHard problems that need careful thinking01Phi 3 Mini 4K Instruct1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Phi 3 Mini 4K Instruct1 of 1 test
- CodingWriting and fixing software10Llama 3 Instruct 8B1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
Long documents and following instructions rest on a single test each.
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 Phi 3 Mini 4K Instruct pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+2.3points ahead
Where Llama 3 Instruct 8B pulls ahead
- Code for real scientific research problemsSciCode+2.9points ahead
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLlama 3 Instruct 8B
- SciCodeLlama 3 Instruct 8B by 2.911.99+2.9
- Terminal-Bench Hardtie00tie
ReasoningPhi 3 Mini 4K Instruct
- GPQA DiamondPhi 3 Mini 4K Instruct by 2.329.631.9+2.3
- Humanity's Last Examtie5.15tie
Long documentsPhi 3 Mini 4K Instruct
- AA-LCRPhi 3 Mini 4K Instruct by 303+3
Other results20 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.
- MATHPhi 3 Mini 4K Instruct by 11.539.150.6+11.5
- MMLUPhi 3 Mini 4K Instruct by 10.760.170.9+10.7
- PIQAPhi 3 Mini 4K Instruct by 7.875.783.5+7.8
- WinoGrandePhi 3 Mini 4K Instruct by 6.66571.6+6.6
- TriviaQALlama 3 Instruct 8B by 6.367.761.4+6.3
- OpenBookQAPhi 3 Mini 4K Instruct by 5.676.682.2+5.6
- HellaSwagPhi 3 Mini 4K Instruct by 4.271.175.3+4.2
- MedQALlama 3 Instruct 8B by 460.556.5+4
- ANLILlama 3 Instruct 8B by 3.757.353.6+3.7
- Social IQAPhi 3 Mini 4K Instruct by 3.773.977.6+3.7
- ARC-ChallengePhi 3 Mini 4K Instruct by 3.582.886.3+3.5
- HumanEvalLlama 3 Instruct 8B by 3.160.457.3+3.1
- AGI EVALLlama 3 Instruct 8B by 34239+3
- BoolQLlama 3 Instruct 8B by 2.880.978.1+2.8
- MBPPPhi 3 Mini 4K Instruct by 2.167.769.8+2.1
- TruthfulQAPhi 3 Mini 4K Instruct by 1.563.264.7+1.5
- Popular aggregated benchmarkPhi 3 Mini 4K Instruct by 1.259.961.1+1.2
- AA IntelligencePhi 3 Mini 4K Instruct by 14.85.8+1
- Artificial Analysis Coding IndexLlama 3 Instruct 8B by 143+1
- τ²-Bench Telecom (AA run)tie00tie
Questions people ask
Which is better, Llama 3 Instruct 8B or Phi 3 Mini 4K Instruct?
Phi 3 Mini 4K Instruct wins two of the four areas where both have results: reasoning and long documents. Llama 3 Instruct 8B wins coding. They are level on following instructions.
Which is better for coding?
Llama 3 Instruct 8B. It wins 1 of the 2 coding tests both models report; Phi 3 Mini 4K Instruct wins none, and 1 is a tie.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 20 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.