# Gemma 4 26B A4B IT vs phi-3-medium 14B

> Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-4-26b-a4b-it-vs-phi-3-medium-14b
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 3 categories and phi-3-medium 14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 4 26B A4B IT leads 45.6 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 73.2% for Gemma 4 26B A4B IT and 27.6% for phi-3-medium 14B.

## Snapshot

| | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| Provider | Google | Microsoft |
| Noometry Index | 43.1 | 29.1 |
| Rank | 88 | 306 |
| Context | 262K | — |
| Input $/M | $0.0765 | — |
| Output $/M | $0.26 | — |
| Weights | Open | Open |

## Coding

- Gemma 4 26B A4B IT: 38.8 (#156)
- phi-3-medium 14B: 36.3 (#198)

| Benchmark | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| LMArena WebDev | 1359 | — |
| SciCode | 40% | — |
| WeirdML | 35.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1446 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 927.17 | — |

## Reasoning

- Gemma 4 26B A4B IT: 21.1 (#205)
- phi-3-medium 14B: —

| Benchmark | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 141.85 | 121.18 |
| CritPt | 0% | — |
| Chess Puzzles | 6% | — |
| LMArena Hard Prompts | 1438 | — |
| DTBench | 74.9% | — |
| LMCA | 29.7% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- Gemma 4 26B A4B IT: 45.7 (#61)
- phi-3-medium 14B: 25.2 (#249)

| Benchmark | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | — |
| LMArena Math | 1469 | — |
| MATH Level 5 | — | 17.6% |

## Knowledge

- Gemma 4 26B A4B IT: 45.6 (#79)
- phi-3-medium 14B: 9.1 (#301)

| Benchmark | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 73.2% | 27.6% |
| Vectara Hallucination Rate | 5.2% | — |
| LMArena Expert | 1447 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multimodal

- Gemma 4 26B A4B IT: 39.9 (#43)
- phi-3-medium 14B: —

| Benchmark | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1260 | — |

## Multilingual

- Gemma 4 26B A4B IT: 53.3 (#68)
- phi-3-medium 14B: —

| Benchmark | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1422 | — |
| LMArena Chinese | 1495 | — |
| LMArena French | 1459 | — |
| LMArena Russian | 1434 | — |
| LMArena Spanish | 1415 | — |

## Instruction Following

- Gemma 4 26B A4B IT: 75.0 (#78)
- phi-3-medium 14B: —

| Benchmark | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1420 | — |

## Long Context

- Gemma 4 26B A4B IT: 43.6 (#87)
- phi-3-medium 14B: —

| Benchmark | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1427 | — |

## Writing & Preference

- Gemma 4 26B A4B IT: 58.8 (#110)
- phi-3-medium 14B: —

| Benchmark | Gemma 4 26B A4B IT | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1434 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1305 | — |
| LMArena Multi-Turn | 1442 | — |

## FAQ

### Is Gemma 4 26B A4B IT better than phi-3-medium 14B?

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 29.1 on the Noometry Index.

### Is Gemma 4 26B A4B IT or phi-3-medium 14B better for coding?

Gemma 4 26B A4B IT scores higher on coding benchmarks: 38.8 versus 36.3 in the Noometry coding category.

### How many benchmarks do Gemma 4 26B A4B IT and phi-3-medium 14B share?

2 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and phi-3-medium 14B has 13.