# Gemma 4 31B IT vs Phi 3 Medium 4k Instruct

> Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-4-31b-it-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and Phi 3 Medium 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.7 to 34.3.

## Snapshot

| | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | Google | Microsoft |
| Noometry Index | 43.2 | 32.4 |
| Rank | 85 | 246 |
| Context | 262K | — |
| Input $/M | $0.09 | — |
| Output $/M | $0.34 | — |
| Weights | Open | Open |

## Coding

- Gemma 4 31B IT: 41.9 (#98)
- Phi 3 Medium 4k Instruct: 32.3 (#263)

| Benchmark | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1459 | 1130 |
| LMArena WebDev | 1364 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |

## Reasoning

- Gemma 4 31B IT: 26.4 (#119)
- Phi 3 Medium 4k Instruct: 20.8 (#214)

| Benchmark | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1127 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |

## Math

- Gemma 4 31B IT: 41.3 (#72)
- Phi 3 Medium 4k Instruct: 30.9 (#202)

| Benchmark | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1464 | 1173 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |

## Knowledge

- Gemma 4 31B IT: 37.9 (#141)
- Phi 3 Medium 4k Instruct: 29.6 (#226)

| Benchmark | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1465 | 1108 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |

## Multimodal

- Gemma 4 31B IT: 41.0 (#32)
- Phi 3 Medium 4k Instruct: —

| Benchmark | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |

## Multilingual

- Gemma 4 31B IT: 54.0 (#52)
- Phi 3 Medium 4k Instruct: 30.8 (#258)

| Benchmark | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1431 | 1094 |
| LMArena Chinese | 1478 | 1108 |
| LMArena French | 1436 | 1109 |
| LMArena Russian | 1462 | 1145 |
| LMArena Spanish | 1443 | 1095 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |

## Instruction Following

- Gemma 4 31B IT: 75.6 (#58)
- Phi 3 Medium 4k Instruct: 57.8 (#263)

| Benchmark | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1433 | 1114 |

## Long Context

- Gemma 4 31B IT: 44.2 (#67)
- Phi 3 Medium 4k Instruct: 33.9 (#250)

| Benchmark | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1446 | 1120 |

## Writing & Preference

- Gemma 4 31B IT: 60.7 (#92)
- Phi 3 Medium 4k Instruct: 34.3 (#267)

| Benchmark | Gemma 4 31B IT | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1443 | 1138 |
| LMArena Creative Writing | 1416 | 1106 |
| LMArena Multi-Turn | 1452 | 1088 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |

## FAQ

### Is Gemma 4 31B IT better than Phi 3 Medium 4k Instruct?

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 32.4 on the Noometry Index.

### Is Gemma 4 31B IT or Phi 3 Medium 4k Instruct better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 32.3 in the Noometry coding category.

### How many benchmarks do Gemma 4 31B IT and Phi 3 Medium 4k Instruct share?

14 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.