# Gemma 3 4B vs Llama 3.2 3B

> Gemma 3 4B and Llama 3.2 3B score almost the same on the Noometry Index (27.9 vs 28.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-llama-3-2-3b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Gemma 3 4B scores higher in 6 categories and Llama 3.2 3B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.2 3B leads 29.1 to 11.8.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.05 / $0.33 for Llama 3.2 3B.

## Snapshot

| | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 27.9 | 28.4 |
| Rank | 320 | 318 |
| Context | 131K | 131K |
| Input $/M | $0.04 | $0.05 |
| Output $/M | $0.08 | $0.33 |
| Weights | Open | Open |

## Coding

- Gemma 3 4B: 35.3 (#214)
- Llama 3.2 3B: 27.1 (#314)

| Benchmark | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1230 | 1098 |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |

## Agentic & Tool Use

- Gemma 3 4B: 20.7 (#134)
- Llama 3.2 3B: 19.9 (#135)

| Benchmark | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | 21.9% |
| BALROG | — | 10.1% |

## Reasoning

- Gemma 3 4B: 12.7 (#330)
- Llama 3.2 3B: 20.1 (#225)

| Benchmark | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1095 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |

## Math

- Gemma 3 4B: 15.8 (#286)
- Llama 3.2 3B: 29.9 (#213)

| Benchmark | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1239 | 1126 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |

## Knowledge

- Gemma 3 4B: 11.8 (#294)
- Llama 3.2 3B: 29.1 (#232)

| Benchmark | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1223 | 1090 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |

## Multilingual

- Gemma 3 4B: 42.7 (#189)
- Llama 3.2 3B: 26.4 (#276)

| Benchmark | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1273 | 1019 |
| LMArena German | 1281 | 1056 |
| LMArena Russian | 1294 | 949 |
| LMArena Chinese | — | 1017 |

## Instruction Following

- Gemma 3 4B: 65.4 (#219)
- Llama 3.2 3B: 56.3 (#270)

| Benchmark | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1239 | 1089 |

## Long Context

- Gemma 3 4B: 38.6 (#189)
- Llama 3.2 3B: 33.4 (#256)

| Benchmark | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1274 | 1101 |

## Writing & Preference

- Gemma 3 4B: 42.2 (#234)
- Llama 3.2 3B: 24.9 (#302)

| Benchmark | Gemma 3 4B | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1291 | 1110 |
| LMArena Creative Writing | 1270 | 1094 |
| EQ-Bench Creative Writing | 1068 | 595 |
| LMArena Multi-Turn | 1255 | 1105 |

## FAQ

### Is Gemma 3 4B better than Llama 3.2 3B?

Gemma 3 4B and Llama 3.2 3B score almost the same on the Noometry Index (27.9 vs 28.4), so choose on price, context window or the category you care about most.

### Which is cheaper, Gemma 3 4B or Llama 3.2 3B?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Llama 3.2 3B lists at $0.05 and $0.33.

### Is Gemma 3 4B or Llama 3.2 3B better for coding?

Gemma 3 4B scores higher on coding benchmarks: 35.3 versus 27.1 in the Noometry coding category.

### Which has the bigger context window?

Both accept 131K tokens.

### How many benchmarks do Gemma 3 4B and Llama 3.2 3B share?

14 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Llama 3.2 3B has 18.