# Granite 3.1 8b Instruct vs Phi 3 Medium 4k Instruct

> Granite 3.1 8b Instruct and Phi 3 Medium 4k Instruct score almost the same on the Noometry Index (32.4 vs 33.0), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 7 categories and Phi 3 Medium 4k Instruct in 1 category; 4 gaps are clear of the uncertainty.

## Snapshot

| | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 32.4 | 33.0 |
| Rank | 258 | 250 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 3.1 8b Instruct: 34.5 (#233)
- Phi 3 Medium 4k Instruct: 32.9 (#268)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1186 | 1130 |

## Agentic & Tool Use

- Granite 3.1 8b Instruct: 24.1 (#120)
- Phi 3 Medium 4k Instruct: —

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |

## Reasoning

- Granite 3.1 8b Instruct: 22.1 (#207)
- Phi 3 Medium 4k Instruct: 21.7 (#214)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1127 |

## Math

- Granite 3.1 8b Instruct: 33.0 (#209)
- Phi 3 Medium 4k Instruct: 33.4 (#202)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1152 | 1173 |

## Knowledge

- Granite 3.1 8b Instruct: 31.1 (#220)
- Phi 3 Medium 4k Instruct: 30.2 (#229)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1142 | 1108 |

## Multilingual

- Granite 3.1 8b Instruct: 30.9 (#260)
- Phi 3 Medium 4k Instruct: 30.6 (#263)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1099 | 1094 |
| LMArena Chinese | 1145 | 1108 |
| LMArena Russian | 1092 | 1145 |
| LMArena French | — | 1110 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Spanish | — | 1095 |

## Instruction Following

- Granite 3.1 8b Instruct: 58.6 (#259)
- Phi 3 Medium 4k Instruct: 57.6 (#268)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1131 | 1113 |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#241)
- Phi 3 Medium 4k Instruct: 34.0 (#255)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1162 | 1120 |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.5 (#266)
- Phi 3 Medium 4k Instruct: 34.1 (#272)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1150 | 1138 |
| LMArena Creative Writing | 1129 | 1107 |
| LMArena Multi-Turn | 1108 | 1088 |

## FAQ

### Is Granite 3.1 8b Instruct better than Phi 3 Medium 4k Instruct?

Granite 3.1 8b Instruct and Phi 3 Medium 4k Instruct score almost the same on the Noometry Index (32.4 vs 33.0), so choose on price, context window or the category you care about most.

### Is Granite 3.1 8b Instruct or Phi 3 Medium 4k Instruct better for coding?

Granite 3.1 8b Instruct scores higher on coding benchmarks: 34.5 versus 32.9 in the Noometry coding category.

### How many benchmarks do Granite 3.1 8b Instruct and Phi 3 Medium 4k Instruct share?

12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.