# Llama 3.2 90B vs Phi-4 Mini

> Phi-4 Mini is the stronger model overall, scoring 30.4 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-90b-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 21.7.

## Snapshot

| | Llama 3.2 90B | Phi-4 Mini |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 27.1 | 30.4 |
| Rank | 326 | 280 |
| Context | — | 128K |
| Input $/M | — | $0.075 |
| Output $/M | — | $0.30 |
| Weights | Open | Open |

## Coding

- Llama 3.2 90B: —
- Phi-4 Mini: 27.6 (#312)

| Benchmark | Llama 3.2 90B | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |

## Agentic & Tool Use

- Llama 3.2 90B: 29.7 (#73)
- Phi-4 Mini: —

| Benchmark | Llama 3.2 90B | Phi-4 Mini |
|---|---|---|
| BALROG | 27.3% | — |

## Reasoning

- Llama 3.2 90B: 20.9 (#207)
- Phi-4 Mini: 21.7 (#190)

| Benchmark | Llama 3.2 90B | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| EnigmaEval | 0.4% | — |
| Epoch Capabilities Index | 125.5 | — |

## Math

- Llama 3.2 90B: 10.4 (#302)
- Phi-4 Mini: —

| Benchmark | Llama 3.2 90B | Phi-4 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| MATH Level 5 | 39.4% | — |

## Knowledge

- Llama 3.2 90B: 21.7 (#269)
- Phi-4 Mini: 24.8 (#261)

| Benchmark | Llama 3.2 90B | Phi-4 Mini |
|---|---|---|
| GPQA Diamond | 41% | — |
| Vectara Hallucination Rate | — | 23.5% |
| MMLU | 80.3% | — |

## Multimodal

- Llama 3.2 90B: 24.9 (#119)
- Phi-4 Mini: —

| Benchmark | Llama 3.2 90B | Phi-4 Mini |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |

## FAQ

### Is Llama 3.2 90B better than Phi-4 Mini?

Phi-4 Mini is the stronger model overall, scoring 30.4 to 27.1 on the Noometry Index.

### How many benchmarks do Llama 3.2 90B and Phi-4 Mini share?

0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Phi-4 Mini has 3.