# Llama 3-8B vs Phi-4 Mini

> Phi-4 Mini is the stronger model overall, scoring 30.4 to 25.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-8b-vs-phi-4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Phi-4 Mini leads 24.8 to 7.8.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.14 / $0.14 for Llama 3-8B.
- Phi-4 Mini accepts more context: 128K tokens versus 8K.

## Snapshot

| | Llama 3-8B | Phi-4 Mini |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 25.3 | 30.4 |
| Rank | 338 | 280 |
| Context | 8K | 128K |
| Input $/M | $0.14 | $0.075 |
| Output $/M | $0.14 | $0.30 |
| Weights | Open | Open |

## Coding

- Llama 3-8B: 30.5 (#285)
- Phi-4 Mini: 27.6 (#312)

| Benchmark | Llama 3-8B | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| BigCodeBench Instruct | 31.9% | — |
| LMArena Coding | 1152 | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |

## Reasoning

- Llama 3-8B: 13.8 (#321)
- Phi-4 Mini: 21.7 (#190)

| Benchmark | Llama 3-8B | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1133 | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.33 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |

## Math

- Llama 3-8B: 8.3 (#317)
- Phi-4 Mini: —

| Benchmark | Llama 3-8B | Phi-4 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | 1151 | — |
| MATH Level 5 | 6.1% | — |

## Knowledge

- Llama 3-8B: 7.8 (#303)
- Phi-4 Mini: 24.8 (#261)

| Benchmark | Llama 3-8B | Phi-4 Mini |
|---|---|---|
| GPQA Diamond | 26.1% | — |
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1113 | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |

## Multilingual

- Llama 3-8B: 31.0 (#256)
- Phi-4 Mini: —

| Benchmark | Llama 3-8B | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1098 | — |
| LMArena Chinese | 1076 | — |
| LMArena French | 1158 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1003 | — |
| LMArena Russian | 1109 | — |
| LMArena Spanish | 1172 | — |

## Instruction Following

- Llama 3-8B: 58.7 (#255)
- Phi-4 Mini: —

| Benchmark | Llama 3-8B | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1127 | — |

## Long Context

- Llama 3-8B: 34.2 (#246)
- Phi-4 Mini: —

| Benchmark | Llama 3-8B | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1128 | — |

## Writing & Preference

- Llama 3-8B: 37.7 (#251)
- Phi-4 Mini: —

| Benchmark | Llama 3-8B | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1166 | — |
| LMArena Creative Writing | 1150 | — |
| LMArena Multi-Turn | 1152 | — |

## FAQ

### Is Llama 3-8B better than Phi-4 Mini?

Phi-4 Mini is the stronger model overall, scoring 30.4 to 25.3 on the Noometry Index.

### Which is cheaper, Llama 3-8B or Phi-4 Mini?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Llama 3-8B lists at $0.14 and $0.14.

### Is Llama 3-8B or Phi-4 Mini better for coding?

Llama 3-8B scores higher on coding benchmarks: 30.5 versus 27.6 in the Noometry coding category.

### Which has the bigger context window?

Phi-4 Mini does, with 128K tokens against 8K.

### How many benchmarks do Llama 3-8B and Phi-4 Mini share?

0 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Phi-4 Mini has 3.