# Phi 3 Medium 4k Instruct vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-4k-instruct-vs-step-3
- Last updated: 2026-10-12
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Phi 3 Medium 4k Instruct scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 34.1.

## Snapshot

| | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | 33.0 | 40.5 |
| Rank | 250 | 149 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Phi 3 Medium 4k Instruct: 32.9 (#268)
- Step 3: 40.1 (#147)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| LMArena Coding | 1130 | 1367 |

## Reasoning

- Phi 3 Medium 4k Instruct: 21.7 (#214)
- Step 3: 28.4 (#105)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1127 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |

## Math

- Phi 3 Medium 4k Instruct: 33.4 (#202)
- Step 3: 37.6 (#148)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| LMArena Math | 1173 | 1366 |

## Knowledge

- Phi 3 Medium 4k Instruct: 30.2 (#229)
- Step 3: 36.8 (#164)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| LMArena Expert | 1108 | 1333 |

## Multimodal

- Phi 3 Medium 4k Instruct: —
- Step 3: 35.5 (#86)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Phi 3 Medium 4k Instruct: 30.6 (#263)
- Step 3: 46.3 (#159)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| LMArena Non-English | 1094 | 1327 |
| LMArena Chinese | 1108 | 1397 |
| LMArena German | 1101 | 1371 |
| LMArena Korean | 954 | 1269 |
| LMArena Russian | 1145 | 1331 |
| LMArena Spanish | 1095 | 1371 |
| LMArena French | 1110 | — |
| LMArena Japanese | 1042 | — |

## Instruction Following

- Phi 3 Medium 4k Instruct: 57.6 (#268)
- Step 3: 70.4 (#164)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1113 | 1332 |

## Long Context

- Phi 3 Medium 4k Instruct: 34.0 (#255)
- Step 3: 40.3 (#157)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| LMArena Longer Query | 1120 | 1326 |

## Writing & Preference

- Phi 3 Medium 4k Instruct: 34.1 (#272)
- Step 3: 54.3 (#151)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3 |
|---|---|---|
| LMArena Text | 1138 | 1350 |
| LMArena Creative Writing | 1107 | 1321 |
| LMArena Multi-Turn | 1088 | 1341 |

## FAQ

### Is Phi 3 Medium 4k Instruct better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 33.0 on the Noometry Index.

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

Step 3 scores higher on coding benchmarks: 40.1 versus 32.9 in the Noometry coding category.

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

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