# Llama 3.2 1B vs Phi 3 Mini 128k Instruct

> Phi 3 Mini 128k Instruct is the stronger model overall, scoring 29.1 to 19.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-1b-vs-phi-3-mini-128k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Llama 3.2 1B scores higher in 2 categories and Phi 3 Mini 128k Instruct in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Mini 128k Instruct leads 29.2 to 9.7.
- The biggest single-benchmark swing is BigCodeBench Complete: 11.3% for Llama 3.2 1B and 40.6% for Phi 3 Mini 128k Instruct.

## Snapshot

| | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 19.9 | 29.1 |
| Rank | 349 | 303 |
| Context | 60K | — |
| Input $/M | $0.027 | — |
| Output $/M | $0.20 | — |
| Weights | Open | Open |

## Coding

- Llama 3.2 1B: 20.6 (#333)
- Phi 3 Mini 128k Instruct: 28.3 (#307)

| Benchmark | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | 8.2% | 29.6% |
| LMArena Coding | 1071 | 1040 |
| BigCodeBench Complete | 11.3% | 40.6% |

## Agentic & Tool Use

- Llama 3.2 1B: 14.5 (#142)
- Phi 3 Mini 128k Instruct: —

| Benchmark | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |

## Reasoning

- Llama 3.2 1B: 15.6 (#304)
- Phi 3 Mini 128k Instruct: 18.7 (#254)

| Benchmark | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1044 | 1028 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 101.95 | — |

## Math

- Llama 3.2 1B: 9.7 (#308)
- Phi 3 Mini 128k Instruct: 29.2 (#220)

| Benchmark | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1086 | 1089 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |

## Knowledge

- Llama 3.2 1B: 7.2 (#307)
- Phi 3 Mini 128k Instruct: 26.3 (#251)

| Benchmark | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1007 | 984 |
| GPQA Diamond | 23.9% | — |

## Multilingual

- Llama 3.2 1B: 23.9 (#287)
- Phi 3 Mini 128k Instruct: 25.4 (#280)

| Benchmark | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 973 | 1000 |
| LMArena Chinese | 958 | 1016 |
| LMArena German | 1014 | 1006 |
| LMArena Russian | 941 | 1004 |
| LMArena French | — | 1038 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
| LMArena Spanish | — | 1058 |

## Instruction Following

- Llama 3.2 1B: 52.6 (#285)
- Phi 3 Mini 128k Instruct: 52.1 (#289)

| Benchmark | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1031 | 1023 |

## Long Context

- Llama 3.2 1B: 31.9 (#269)
- Phi 3 Mini 128k Instruct: 30.3 (#284)

| Benchmark | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1050 | 996 |

## Writing & Preference

- Llama 3.2 1B: 21.4 (#305)
- Phi 3 Mini 128k Instruct: 27.3 (#296)

| Benchmark | Llama 3.2 1B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1055 | 1050 |
| LMArena Creative Writing | 1033 | 1024 |
| LMArena Multi-Turn | 1030 | 989 |
| EQ-Bench Creative Writing | 200 | — |

## FAQ

### Is Llama 3.2 1B better than Phi 3 Mini 128k Instruct?

Phi 3 Mini 128k Instruct is the stronger model overall, scoring 29.1 to 19.9 on the Noometry Index.

### Is Llama 3.2 1B or Phi 3 Mini 128k Instruct better for coding?

Phi 3 Mini 128k Instruct scores higher on coding benchmarks: 28.3 versus 20.6 in the Noometry coding category.

### How many benchmarks do Llama 3.2 1B and Phi 3 Mini 128k Instruct share?

15 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.