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

> Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-phi-3-mini-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 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 3.1 8b Instruct leads 58.6 to 47.7.

## Snapshot

| | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 32.4 | 27.9 |
| Rank | 258 | 328 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 3.1 8b Instruct: 34.5 (#233)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1186 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Agentic & Tool Use

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

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

## Reasoning

- Granite 3.1 8b Instruct: 22.1 (#207)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- Granite 3.1 8b Instruct: 33.0 (#209)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1152 | 1111 |
| LiveBench Math | — | 15.7% |

## Knowledge

- Granite 3.1 8b Instruct: 31.1 (#220)
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1142 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multilingual

- Granite 3.1 8b Instruct: 30.9 (#260)
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1099 | 1021 |
| LMArena Chinese | 1145 | 1021 |
| LMArena Russian | 1092 | 1022 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Spanish | — | 1085 |

## Instruction Following

- Granite 3.1 8b Instruct: 58.6 (#259)
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1131 | 1053 |
| LiveBench Instruction Following | — | 39.1% |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#241)
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1162 | 1044 |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.5 (#266)
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1150 | 1073 |
| LMArena Creative Writing | 1129 | 1037 |
| LMArena Multi-Turn | 1108 | 1018 |
| LiveBench Language | — | 9.2% |

## FAQ

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

Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 27.9 on the Noometry Index.

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

Granite 3.1 8b Instruct scores higher on coding benchmarks: 34.5 versus 26.6 in the Noometry coding category.

### How many benchmarks do Granite 3.1 8b Instruct and Phi 3 Mini 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 Mini 4k Instruct has 35.