# Phi 3 Medium 4k Instruct vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-4k-instruct-vs-step-3-5-flash
- 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 0 categories and Step 3.5 Flash in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 59.0 to 34.3.

## Snapshot

| | Phi 3 Medium 4k Instruct | Step 3.5 Flash |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | 32.4 | 41.7 |
| Rank | 246 | 116 |
| Context | — | 256K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.30 |
| Weights | Open | Open |

## Coding

- Phi 3 Medium 4k Instruct: 32.3 (#263)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1130 | 1436 |

## Reasoning

- Phi 3 Medium 4k Instruct: 20.8 (#214)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1127 | 1411 |
| NYT Connections (extended) | — | 28.4% |

## Math

- Phi 3 Medium 4k Instruct: 30.9 (#202)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1173 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- Phi 3 Medium 4k Instruct: 29.6 (#226)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1108 | 1422 |

## Multilingual

- Phi 3 Medium 4k Instruct: 30.8 (#258)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1094 | 1386 |
| LMArena Chinese | 1108 | 1448 |
| LMArena French | 1109 | 1421 |
| LMArena German | 1101 | 1404 |
| LMArena Japanese | 1042 | 1353 |
| LMArena Korean | 954 | 1350 |
| LMArena Russian | 1145 | 1385 |
| LMArena Spanish | 1095 | 1419 |

## Instruction Following

- Phi 3 Medium 4k Instruct: 57.8 (#263)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1114 | 1385 |

## Long Context

- Phi 3 Medium 4k Instruct: 33.9 (#250)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1120 | 1402 |

## Writing & Preference

- Phi 3 Medium 4k Instruct: 34.3 (#267)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Phi 3 Medium 4k Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1138 | 1403 |
| LMArena Creative Writing | 1106 | 1357 |
| LMArena Multi-Turn | 1088 | 1405 |

## FAQ

### Is Phi 3 Medium 4k Instruct better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 32.4 on the Noometry Index.

### Is Phi 3 Medium 4k Instruct or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 32.3 in the Noometry coding category.

### How many benchmarks do Phi 3 Medium 4k Instruct and Step 3.5 Flash share?

17 benchmarks have published results for both models. Phi 3 Medium 4k Instruct has 17 scored results on Noometry and Step 3.5 Flash has 19.
