# Gemma 7B vs Llama 3.2 90B

> Gemma 7B is the stronger model overall, scoring 29.5 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-7b-vs-llama-3-2-90b
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Gemma 7B scores higher in 2 categories and Llama 3.2 90B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 7B leads 28.7 to 10.4.

## Snapshot

| | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 29.5 | 27.1 |
| Rank | 295 | 326 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Gemma 7B: 29.9 (#290)
- Llama 3.2 90B: —

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| LMArena Coding | 1048 | — |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |

## Agentic & Tool Use

- Gemma 7B: —
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |

## Reasoning

- Gemma 7B: 19.0 (#247)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 111.74 | 125.5 |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1042 | — |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |

## Math

- Gemma 7B: 28.7 (#225)
- Llama 3.2 90B: 10.4 (#302)

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1066 | — |
| MATH Level 5 | — | 39.4% |
| GSM8K | 46.4% | — |

## Knowledge

- Gemma 7B: 26.8 (#248)
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| MMLU | 66.1% | 80.3% |
| GPQA Diamond | — | 41% |
| LMArena Expert | 1002 | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |

## Multimodal

- Gemma 7B: —
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## Multilingual

- Gemma 7B: 25.3 (#282)
- Llama 3.2 90B: —

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 999 | — |
| LMArena Chinese | 1035 | — |
| LMArena French | 1024 | — |
| LMArena Russian | 993 | — |

## Instruction Following

- Gemma 7B: 51.7 (#290)
- Llama 3.2 90B: —

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1017 | — |

## Long Context

- Gemma 7B: 31.1 (#277)
- Llama 3.2 90B: —

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1022 | — |

## Writing & Preference

- Gemma 7B: 27.2 (#297)
- Llama 3.2 90B: —

| Benchmark | Gemma 7B | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1056 | — |
| LMArena Creative Writing | 1024 | — |
| LMArena Multi-Turn | 963 | — |

## FAQ

### Is Gemma 7B better than Llama 3.2 90B?

Gemma 7B is the stronger model overall, scoring 29.5 to 27.1 on the Noometry Index.

### How many benchmarks do Gemma 7B and Llama 3.2 90B share?

2 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Llama 3.2 90B has 9.