# Gemma 3 1B vs Llama 3.2 90B

> Llama 3.2 90B is the stronger model overall, scoring 27.1 to 20.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-1b-vs-llama-3-2-90b
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Gemma 3 1B scores higher in 0 categories and Llama 3.2 90B in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Llama 3.2 90B leads 29.7 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 19.9% for Gemma 3 1B and 41% for Llama 3.2 90B.

## Snapshot

| | Gemma 3 1B | Llama 3.2 90B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 20.7 | 27.1 |
| Rank | 348 | 326 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Agentic & Tool Use

- Gemma 3 1B: 13.5 (#144)
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | Gemma 3 1B | Llama 3.2 90B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 7.2% | — |
| BALROG | — | 27.3% |

## Reasoning

- Gemma 3 1B: 18.5 (#260)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | Gemma 3 1B | Llama 3.2 90B |
|---|---|---|
| Chess Puzzles | 0% | — |
| EnigmaEval | — | 0.4% |
| Epoch Capabilities Index | — | 125.5 |

## Math

- Gemma 3 1B: 9.6 (#310)
- Llama 3.2 90B: 10.4 (#302)

| Benchmark | Gemma 3 1B | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 2.6% |
| MATH Level 5 | — | 39.4% |

## Knowledge

- Gemma 3 1B: 7.1 (#309)
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | Gemma 3 1B | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 19.9% | 41% |
| MMLU | — | 80.3% |

## Multimodal

- Gemma 3 1B: —
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | Gemma 3 1B | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## FAQ

### Is Gemma 3 1B better than Llama 3.2 90B?

Llama 3.2 90B is the stronger model overall, scoring 27.1 to 20.7 on the Noometry Index.

### How many benchmarks do Gemma 3 1B and Llama 3.2 90B share?

2 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and Llama 3.2 90B has 9.