# Llama 3.2 1B vs phi-3-medium 14B

> phi-3-medium 14B is the stronger model overall, scoring 29.7 to 20.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-1b-vs-phi-3-medium-14b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and phi-3-medium 14B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where phi-3-medium 14B leads 27.3 to 10.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 11.3% for Llama 3.2 1B and 48.7% for phi-3-medium 14B.

## Snapshot

| | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 20.1 | 29.7 |
| Rank | 354 | 306 |
| Context | 60K | — |
| Input $/M | $0.027 | — |
| Output $/M | $0.20 | — |
| Weights | Open | Open |

## Coding

- Llama 3.2 1B: 21.1 (#338)
- phi-3-medium 14B: 36.8 (#201)

| Benchmark | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | 8.2% | 37.6% |
| BigCodeBench Complete | 11.3% | 48.7% |
| LMArena Coding | 1070 | — |

## Agentic & Tool Use

- Llama 3.2 1B: 14.6 (#150)
- phi-3-medium 14B: —

| Benchmark | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |

## Reasoning

- Llama 3.2 1B: 16.2 (#308)
- phi-3-medium 14B: —

| Benchmark | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 101.99 | 121.23 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1044 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- Llama 3.2 1B: 10.4 (#313)
- phi-3-medium 14B: 27.3 (#250)

| Benchmark | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LMArena Math | 1086 | — |
| MATH Level 5 | — | 17.6% |

## Knowledge

- Llama 3.2 1B: 7.2 (#312)
- phi-3-medium 14B: 9.1 (#306)

| Benchmark | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 23.9% | 27.6% |
| LMArena Expert | 1007 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- Llama 3.2 1B: 23.8 (#292)
- phi-3-medium 14B: —

| Benchmark | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 973 | — |
| LMArena Chinese | 959 | — |
| LMArena German | 1014 | — |
| LMArena Russian | 941 | — |

## Instruction Following

- Llama 3.2 1B: 52.4 (#290)
- phi-3-medium 14B: —

| Benchmark | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1031 | — |

## Long Context

- Llama 3.2 1B: 31.9 (#274)
- phi-3-medium 14B: —

| Benchmark | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1050 | — |

## Writing & Preference

- Llama 3.2 1B: 21.3 (#310)
- phi-3-medium 14B: —

| Benchmark | Llama 3.2 1B | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1055 | — |
| LMArena Creative Writing | 1033 | — |
| EQ-Bench Creative Writing | 200 | — |
| LMArena Multi-Turn | 1030 | — |

## FAQ

### Is Llama 3.2 1B better than phi-3-medium 14B?

phi-3-medium 14B is the stronger model overall, scoring 29.7 to 20.1 on the Noometry Index.

### Is Llama 3.2 1B or phi-3-medium 14B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 21.1 in the Noometry coding category.

### How many benchmarks do Llama 3.2 1B and phi-3-medium 14B share?

4 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and phi-3-medium 14B has 13.