# Llama 13b vs Phi 3 Mini 4k Instruct

> Phi 3 Mini 4k Instruct is the stronger model overall, scoring 27.9 to 24.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-13b-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Llama 13b scores higher in 1 category and Phi 3 Mini 4k Instruct in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi 3 Mini 4k Instruct leads 27.6 to 13.8.

## Snapshot

| | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 24.4 | 27.9 |
| Rank | 348 | 328 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama 13b: 21.4 (#337)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 683 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- Llama 13b: 14.0 (#329)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 728 | 1072 |
| BIG-Bench Hard | 37.9% | 71.7% |
| HellaSwag | 79.2% | 76.7% |
| WinoGrande | 73% | 70.8% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| Epoch Capabilities Index | 100.58 | — |
| LAMBADA | 75.2% | — |
| LiveBench | — | 22.4% |
| PIQA | 80.1% | — |

## Math

- Llama 13b: 26.7 (#256)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 838 | 1111 |
| LiveBench Math | — | 15.7% |
| GSM8K | 20.6% | — |

## Knowledge

- Llama 13b: —
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | 84.9% |
| MMLU | 47.7% | 68.8% |
| OpenBookQA | 56.4% | 88% |
| TriviaQA | 77.9% | 64% |
| LMArena Expert | — | 1045 |
| BoolQ | 78.7% | — |

## Multimodal

- Llama 13b: —
- Phi 3 Mini 4k Instruct: —

| Benchmark | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| ScienceQA | 43.3% | — |

## Multilingual

- Llama 13b: 16.6 (#297)
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 819 | 1021 |
| LMArena Chinese | — | 1021 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1085 |

## Instruction Following

- Llama 13b: 36.7 (#305)
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 781 | 1053 |
| LiveBench Instruction Following | — | 39.1% |

## Long Context

- Llama 13b: —
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1044 |

## Writing & Preference

- Llama 13b: 13.8 (#312)
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | Llama 13b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 834 | 1073 |
| LMArena Creative Writing | 794 | 1037 |
| LMArena Multi-Turn | 753 | 1018 |
| LiveBench Language | — | 9.2% |

## FAQ

### Is Llama 13b better than Phi 3 Mini 4k Instruct?

Phi 3 Mini 4k Instruct is the stronger model overall, scoring 27.9 to 24.4 on the Noometry Index.

### Is Llama 13b or Phi 3 Mini 4k Instruct better for coding?

Phi 3 Mini 4k Instruct scores higher on coding benchmarks: 26.6 versus 21.4 in the Noometry coding category.

### How many benchmarks do Llama 13b and Phi 3 Mini 4k Instruct share?

15 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.