# Gemma 3 12B vs Phi 3 Mini 128k Instruct

> Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-phi-3-mini-128k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Phi 3 Mini 128k Instruct in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 12B leads 45.7 to 25.2.

## Snapshot

| | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| Provider | Google | Microsoft |
| Noometry Index | 32.1 | 29.7 |
| Rank | 262 | 305 |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.15 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.7 (#280)
- Phi 3 Mini 128k Instruct: 28.8 (#312)

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1281 | 1039 |
| SciCode | 17.4% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |

## Agentic & Tool Use

- Gemma 3 12B: 25.5 (#108)
- Phi 3 Mini 128k Instruct: —

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.7 (#313)
- Phi 3 Mini 128k Instruct: 19.6 (#256)

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1028 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |

## Math

- Gemma 3 12B: 22.3 (#279)
- Phi 3 Mini 128k Instruct: 31.6 (#222)

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1307 | 1089 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |

## Knowledge

- Gemma 3 12B: 26.5 (#257)
- Phi 3 Mini 128k Instruct: 26.8 (#254)

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1248 | 984 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |

## Multimodal

- Gemma 3 12B: —
- Phi 3 Mini 128k Instruct: —

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.7 (#165)
- Phi 3 Mini 128k Instruct: 25.2 (#285)

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1318 | 1000 |
| LMArena German | 1370 | 1006 |
| LMArena Russian | 1335 | 1004 |
| LMArena Chinese | — | 1016 |
| LMArena French | — | 1039 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
| LMArena Spanish | — | 1059 |

## Instruction Following

- Gemma 3 12B: 68.6 (#186)
- Phi 3 Mini 128k Instruct: 51.8 (#294)

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1299 | 1023 |

## Long Context

- Gemma 3 12B: 40.0 (#162)
- Phi 3 Mini 128k Instruct: 30.4 (#289)

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1317 | 996 |

## Writing & Preference

- Gemma 3 12B: 47.5 (#209)
- Phi 3 Mini 128k Instruct: 27.1 (#301)

| Benchmark | Gemma 3 12B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1334 | 1050 |
| LMArena Creative Writing | 1331 | 1024 |
| LMArena Multi-Turn | 1334 | 989 |
| EQ-Bench Creative Writing | 1126 | — |

## FAQ

### Is Gemma 3 12B better than Phi 3 Mini 128k Instruct?

Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.7 on the Noometry Index.

### Is Gemma 3 12B or Phi 3 Mini 128k Instruct better for coding?

Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 28.8 in the Noometry coding category.

### How many benchmarks do Gemma 3 12B and Phi 3 Mini 128k Instruct share?

12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.