# Gemma 3 27B vs Llama 3.2 1B

> Gemma 3 27B is the stronger model overall, scoring 30.5 to 19.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-27b-vs-llama-3-2-1b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemma 3 27B scores higher in 8 categories and Llama 3.2 1B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.7 to 21.4.
- The biggest single-benchmark swing is GPQA Diamond: 47.7% for Gemma 3 27B and 23.9% for Llama 3.2 1B.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.08 / $0.16 for Gemma 3 27B.
- Gemma 3 27B accepts more context: 131K tokens versus 60K.

## Snapshot

| | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 30.5 | 19.9 |
| Rank | 277 | 349 |
| Context | 131K | 60K |
| Input $/M | $0.08 | $0.027 |
| Output $/M | $0.16 | $0.20 |
| Weights | Open | Open |

## Coding

- Gemma 3 27B: 22.1 (#329)
- Llama 3.2 1B: 20.6 (#333)

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| LMArena Coding | 1322 | 1071 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| BigCodeBench Instruct | — | 8.2% |
| LiveBench Coding | 39.9% | — |
| BigCodeBench Complete | — | 11.3% |

## Agentic & Tool Use

- Gemma 3 27B: 24.9 (#105)
- Llama 3.2 1B: 14.5 (#142)

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | 10.8% |
| BALROG | — | 6.6% |

## Reasoning

- Gemma 3 27B: 16.3 (#297)
- Llama 3.2 1B: 15.6 (#304)

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1340 | 1044 |
| Epoch Capabilities Index | 130.04 | 101.95 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| LiveBench | 50% | — |

## Math

- Gemma 3 27B: 24.4 (#261)
- Llama 3.2 1B: 9.7 (#308)

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 0.6% |
| LMArena Math | 1312 | 1086 |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |

## Knowledge

- Gemma 3 27B: 25.4 (#256)
- Llama 3.2 1B: 7.2 (#307)

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| GPQA Diamond | 47.7% | 23.9% |
| LMArena Expert | 1303 | 1007 |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |

## Multimodal

- Gemma 3 27B: 32.0 (#94)
- Llama 3.2 1B: —

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| LMArena Vision | 1165 | — |
| GeoBench | 52% | — |

## Multilingual

- Gemma 3 27B: 47.0 (#150)
- Llama 3.2 1B: 23.9 (#287)

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| LMArena Non-English | 1334 | 973 |
| LMArena Chinese | 1347 | 958 |
| LMArena German | 1362 | 1014 |
| LMArena Russian | 1349 | 941 |
| LMArena French | 1368 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1348 | — |

## Instruction Following

- Gemma 3 27B: 70.8 (#155)
- Llama 3.2 1B: 52.6 (#285)

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1031 |
| LiveBench Instruction Following | 74.9% | — |

## Long Context

- Gemma 3 27B: 27.6 (#288)
- Llama 3.2 1B: 31.9 (#269)

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| LMArena Longer Query | 1333 | 1050 |
| Fiction.LiveBench | 33.3% | — |

## Writing & Preference

- Gemma 3 27B: 52.7 (#161)
- Llama 3.2 1B: 21.4 (#305)

| Benchmark | Gemma 3 27B | Llama 3.2 1B |
|---|---|---|
| LMArena Text | 1358 | 1055 |
| LMArena Creative Writing | 1346 | 1033 |
| EQ-Bench Creative Writing | 1266 | 200 |
| LMArena Multi-Turn | 1344 | 1030 |
| Short-Story Creative Writing | 79.9% | — |
| LiveBench Language | 34.6% | — |

## FAQ

### Is Gemma 3 27B better than Llama 3.2 1B?

Gemma 3 27B is the stronger model overall, scoring 30.5 to 19.9 on the Noometry Index.

### Which is cheaper, Gemma 3 27B or Llama 3.2 1B?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Gemma 3 27B lists at $0.08 and $0.16.

### Is Gemma 3 27B or Llama 3.2 1B better for coding?

Gemma 3 27B scores higher on coding benchmarks: 22.1 versus 20.6 in the Noometry coding category.

### Which has the bigger context window?

Gemma 3 27B does, with 131K tokens against 60K.

### How many benchmarks do Gemma 3 27B and Llama 3.2 1B share?

19 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Llama 3.2 1B has 22.