# Phi 3 Medium 4k Instruct vs Phi 3 Small 8k Instruct

> Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-4k-instruct-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Phi 3 Medium 4k Instruct scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Phi 3 Medium 4k Instruct leads 20.8 to 14.2.

## Snapshot

| | Phi 3 Medium 4k Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | Microsoft | Microsoft |
| Noometry Index | 32.4 | 28.8 |
| Rank | 246 | 310 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Phi 3 Medium 4k Instruct: 32.3 (#263)
- Phi 3 Small 8k Instruct: 27.4 (#313)

| Benchmark | Phi 3 Medium 4k Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1130 | 1102 |
| LiveBench Coding | — | 20.3% |

## Reasoning

- Phi 3 Medium 4k Instruct: 20.8 (#214)
- Phi 3 Small 8k Instruct: 14.2 (#319)

| Benchmark | Phi 3 Medium 4k Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1127 | 1100 |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- Phi 3 Medium 4k Instruct: 30.9 (#202)
- Phi 3 Small 8k Instruct: 25.4 (#247)

| Benchmark | Phi 3 Medium 4k Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1173 | 1151 |
| LiveBench Math | — | 17.6% |

## Knowledge

- Phi 3 Medium 4k Instruct: 29.6 (#226)
- Phi 3 Small 8k Instruct: 28.5 (#237)

| Benchmark | Phi 3 Medium 4k Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1108 | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- Phi 3 Medium 4k Instruct: 30.8 (#258)
- Phi 3 Small 8k Instruct: 28.6 (#267)

| Benchmark | Phi 3 Medium 4k Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1094 | 1058 |
| LMArena Chinese | 1108 | 1061 |
| LMArena French | 1109 | 1134 |
| LMArena German | 1101 | 1080 |
| LMArena Japanese | 1042 | 966 |
| LMArena Korean | 954 | 894 |
| LMArena Russian | 1145 | 1111 |
| LMArena Spanish | 1095 | 1111 |

## Instruction Following

- Phi 3 Medium 4k Instruct: 57.8 (#263)
- Phi 3 Small 8k Instruct: 52.2 (#287)

| Benchmark | Phi 3 Medium 4k Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1114 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- Phi 3 Medium 4k Instruct: 33.9 (#250)
- Phi 3 Small 8k Instruct: 33.0 (#262)

| Benchmark | Phi 3 Medium 4k Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1120 | 1088 |

## Writing & Preference

- Phi 3 Medium 4k Instruct: 34.3 (#267)
- Phi 3 Small 8k Instruct: 31.3 (#279)

| Benchmark | Phi 3 Medium 4k Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1138 | 1110 |
| LMArena Creative Writing | 1106 | 1083 |
| LMArena Multi-Turn | 1088 | 1068 |
| LiveBench Language | — | 12.9% |

## FAQ

### Is Phi 3 Medium 4k Instruct better than Phi 3 Small 8k Instruct?

Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 28.8 on the Noometry Index.

### Is Phi 3 Medium 4k Instruct or Phi 3 Small 8k Instruct better for coding?

Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.3 versus 27.4 in the Noometry coding category.

### How many benchmarks do Phi 3 Medium 4k Instruct and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. Phi 3 Medium 4k Instruct has 17 scored results on Noometry and Phi 3 Small 8k Instruct has 32.