# Phi 3 Mini 4k Instruct June 2024 vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 31.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-4k-instruct-june-vs-step-5-preview
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Phi 3 Mini 4k Instruct June 2024 scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 29.6.
- Phi 3 Mini 4k Instruct June 2024 has downloadable open weights; the other is API-only.

## Snapshot

| | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | 31.3 | 47.9 |
| Rank | 276 | 58 |
| Context | — | 1.02M |
| Input $/M | — | $1 |
| Output $/M | — | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Phi 3 Mini 4k Instruct June 2024: 31.8 (#279)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1093 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |

## Reasoning

- Phi 3 Mini 4k Instruct June 2024: 20.8 (#231)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1087 | 1465 |
| CritPt | — | 20.9% |

## Math

- Phi 3 Mini 4k Instruct June 2024: 33.0 (#208)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| LMArena Math | 1152 | 1470 |
| ProofBench | — | 42% |

## Knowledge

- Phi 3 Mini 4k Instruct June 2024: 28.6 (#244)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1051 | 1470 |

## Multimodal

- Phi 3 Mini 4k Instruct June 2024: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- Phi 3 Mini 4k Instruct June 2024: 25.9 (#282)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1013 | 1432 |
| LMArena Chinese | 1033 | 1519 |
| LMArena Russian | 1019 | 1436 |
| LMArena German | 1031 | — |
| LMArena Japanese | 954 | — |
| LMArena Korean | 880 | — |
| LMArena Spanish | — | 1439 |

## Instruction Following

- Phi 3 Mini 4k Instruct June 2024: 54.1 (#282)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1058 | 1444 |

## Long Context

- Phi 3 Mini 4k Instruct June 2024: 31.7 (#277)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1042 | 1455 |

## Writing & Preference

- Phi 3 Mini 4k Instruct June 2024: 29.6 (#294)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1080 | 1442 |
| LMArena Creative Writing | 1045 | 1410 |
| LMArena Multi-Turn | 1049 | 1447 |

## FAQ

### Is Phi 3 Mini 4k Instruct June 2024 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 31.3 on the Noometry Index.

### Is Phi 3 Mini 4k Instruct June 2024 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 31.8 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 4k Instruct June 2024 and Step 5 Preview share?

12 benchmarks have published results for both models. Phi 3 Mini 4k Instruct June 2024 has 15 scored results on Noometry and Step 5 Preview has 18.
