# Llama 3.2 90B vs Phi 3 Medium 4k Instruct

> Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-90b-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Phi 3 Medium 4k Instruct leads 30.9 to 10.4.

## Snapshot

| | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 27.1 | 32.4 |
| Rank | 326 | 246 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama 3.2 90B: —
- Phi 3 Medium 4k Instruct: 32.3 (#263)

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | — | 1130 |

## Agentic & Tool Use

- Llama 3.2 90B: 29.7 (#73)
- Phi 3 Medium 4k Instruct: —

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| BALROG | 27.3% | — |

## Reasoning

- Llama 3.2 90B: 20.9 (#207)
- Phi 3 Medium 4k Instruct: 20.8 (#214)

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1127 |
| Epoch Capabilities Index | 125.5 | — |

## Math

- Llama 3.2 90B: 10.4 (#302)
- Phi 3 Medium 4k Instruct: 30.9 (#202)

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1173 |
| MATH Level 5 | 39.4% | — |

## Knowledge

- Llama 3.2 90B: 21.7 (#269)
- Phi 3 Medium 4k Instruct: 29.6 (#226)

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1108 |
| MMLU | 80.3% | — |

## Multimodal

- Llama 3.2 90B: 24.9 (#119)
- Phi 3 Medium 4k Instruct: —

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |

## Multilingual

- Llama 3.2 90B: —
- Phi 3 Medium 4k Instruct: 30.8 (#258)

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1094 |
| LMArena Chinese | — | 1108 |
| LMArena French | — | 1109 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Russian | — | 1145 |
| LMArena Spanish | — | 1095 |

## Instruction Following

- Llama 3.2 90B: —
- Phi 3 Medium 4k Instruct: 57.8 (#263)

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1114 |

## Long Context

- Llama 3.2 90B: —
- Phi 3 Medium 4k Instruct: 33.9 (#250)

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1120 |

## Writing & Preference

- Llama 3.2 90B: —
- Phi 3 Medium 4k Instruct: 34.3 (#267)

| Benchmark | Llama 3.2 90B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | — | 1138 |
| LMArena Creative Writing | — | 1106 |
| LMArena Multi-Turn | — | 1088 |

## FAQ

### Is Llama 3.2 90B better than Phi 3 Medium 4k Instruct?

Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 27.1 on the Noometry Index.

### How many benchmarks do Llama 3.2 90B and Phi 3 Medium 4k Instruct share?

0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.