# Gemma 2 9B vs Phi-2

> Gemma 2 9B has enough public results to be ranked (#341); Phi-2 does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-phi-2
- Last updated: 2026-10-11
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both.

## Snapshot

| | Gemma 2 9B | Phi-2 |
|---|---|---|
| Provider | Google | Microsoft |
| Noometry Index | 25.9 | — |
| Rank | 341 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Gemma 2 9B: 29.4 (#304)
- Phi-2: —

| Benchmark | Gemma 2 9B | Phi-2 |
|---|---|---|
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| LMArena Coding | 1173 | — |
| BigCodeBench Complete | 40.6% | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- Gemma 2 9B: 15.9 (#309)
- Phi-2: —

| Benchmark | Gemma 2 9B | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 119.83 | 107.94 |
| LiveBench Reasoning | 15.2% | — |
| LMArena Hard Prompts | 1171 | — |
| LiveBench Data Analysis | 36.4% | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
| WinoGrande | — | 54.7% |

## Math

- Gemma 2 9B: 9.9 (#318)
- Phi-2: —

| Benchmark | Gemma 2 9B | Phi-2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| LMArena Math | 1183 | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#305)
- Phi-2: —

| Benchmark | Gemma 2 9B | Phi-2 |
|---|---|---|
| MMLU | 72.1% | 58.4% |
| GPQA Diamond | 27.5% | — |
| LMArena Expert | 1147 | — |
| ARC (AI2) Challenge | — | 75.9% |
| BoolQ | 85.7% | — |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |

## Multilingual

- Gemma 2 9B: 36.6 (#238)
- Phi-2: —

| Benchmark | Gemma 2 9B | Phi-2 |
|---|---|---|
| LMArena Non-English | 1188 | — |
| LMArena Chinese | 1185 | — |
| LMArena French | 1190 | — |
| LMArena German | 1186 | — |
| LMArena Japanese | 1144 | — |
| LMArena Korean | 1137 | — |
| LMArena Russian | 1200 | — |
| LMArena Spanish | 1200 | — |

## Instruction Following

- Gemma 2 9B: 57.6 (#269)
- Phi-2: —

| Benchmark | Gemma 2 9B | Phi-2 |
|---|---|---|
| LiveBench Instruction Following | 52.6% | — |
| LMArena Instruction Following | 1178 | — |

## Long Context

- Gemma 2 9B: 36.3 (#233)
- Phi-2: —

| Benchmark | Gemma 2 9B | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1197 | — |

## Writing & Preference

- Gemma 2 9B: 32.1 (#281)
- Phi-2: —

| Benchmark | Gemma 2 9B | Phi-2 |
|---|---|---|
| LMArena Text | 1207 | — |
| LMArena Creative Writing | 1206 | — |
| EQ-Bench Creative Writing | 841 | — |
| LMArena Multi-Turn | 1193 | — |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than Phi-2?

Gemma 2 9B has enough public results to be ranked (#341); Phi-2 does not yet, so treat this comparison as directional.

### How many benchmarks do Gemma 2 9B and Phi-2 share?

2 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Phi-2 has 11.