Llama 3 Instruct 8B vs Phi 4 Mini Instruct
Wins 2 of 5 areas
Coding · Following instructions
Wins 3 of 5 areas
Reasoning · Facts · Long documents
Phi 4 Mini Instruct is the stronger all-rounder.Llama 3 Instruct 8B is better at coding.
Scores updated · 24 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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 4 Mini Instruct1 of 3 tests · 2 ties
- FactsGetting facts right instead of making them up01Phi 4 Mini Instruct1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Phi 4 Mini Instruct1 of 1 test
- CodingWriting and fixing software10Llama 3 Instruct 8B1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked10Llama 3 Instruct 8B1 of 1 test
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 4 Mini Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+11.8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.5points ahead
Every test, side by side
All 24 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 1.111.910.8+1.1
- Terminal-Bench Hardtie00tie
ReasoningPhi 4 Mini Instruct
- GPQA DiamondPhi 4 Mini Instruct by 3.529.633.1+3.5
- Humanity's Last Examtie5.14.5tie
- CritPttie00tie
FactsPhi 4 Mini Instruct
- AA-Omniscience · Non-hallucinationPhi 4 Mini Instruct by 11.810.222+11.8
- AA-Omniscience · Accuracytie10.49.5tie
Long documentsPhi 4 Mini Instruct
- AA-LCRPhi 4 Mini Instruct by 15.3015.3+15.3
Following instructionsLlama 3 Instruct 8B
- IFBenchLlama 3 Instruct 8B by 3.524.621.1+3.5
Other results15 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.
- GSM8KPhi 4 Mini Instruct by 38.749.988.6+38.7
- MMLU-ProPhi 4 Mini Instruct by 17.435.452.8+17.4
- BBHPhi 4 Mini Instruct by 12.757.770.4+12.7
- AA-OmnisciencePhi 4 Mini Instruct by 9-70.1-61.1+9
- τ²-Bench Telecom (AA run)Phi 4 Mini Instruct by 8.208.2+8.2
- TruthfulQAPhi 4 Mini Instruct by 3.263.266.4+3.2
- OpenBookQAPhi 4 Mini Instruct by 2.676.679.2+2.6
- HellaSwagLlama 3 Instruct 8B by 271.169.1+2
- WinoGrandePhi 4 Mini Instruct by 26567+2
- PIQAPhi 4 Mini Instruct by 1.975.777.6+1.9
- AA IntelligencePhi 4 Mini Instruct by 1.54.86.3+1.5
- Social IQALlama 3 Instruct 8B by 1.473.972.5+1.4
- ARC-Challengetie82.883.7tie
- BoolQtie80.981.2tie
- Artificial Analysis Coding Indextie43.8tie
Questions people ask
Which is better, Llama 3 Instruct 8B or Phi 4 Mini Instruct?
Phi 4 Mini Instruct wins three of the five areas where both have results: reasoning, facts and long documents. Llama 3 Instruct 8B wins coding and following instructions.
Which is better for coding?
Llama 3 Instruct 8B. It wins 1 of the 2 coding tests both models report; Phi 4 Mini Instruct wins none, and 1 is a tie.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.