# Gemma 3 27B vs Llama 13b

> Gemma 3 27B is the stronger model overall, scoring 30.5 to 23.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-27b-vs-llama-13b
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Gemma 3 27B scores higher in 5 categories and Llama 13b in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.7 to 13.9.

## Snapshot

| | Gemma 3 27B | Llama 13b |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 30.5 | 23.9 |
| Rank | 277 | 344 |
| Context | 131K | — |
| Input $/M | $0.08 | — |
| Output $/M | $0.16 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 27B: 22.1 (#329)
- Llama 13b: 20.9 (#332)

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| LMArena Coding | 1322 | 683 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |

## Agentic & Tool Use

- Gemma 3 27B: 24.9 (#105)
- Llama 13b: —

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |

## Reasoning

- Gemma 3 27B: 16.3 (#297)
- Llama 13b: 13.4 (#327)

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1340 | 728 |
| Epoch Capabilities Index | 130.04 | 100.09 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| LiveBench | 50% | — |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |

## Math

- Gemma 3 27B: 24.4 (#261)
- Llama 13b: 24.4 (#259)

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| LMArena Math | 1312 | 838 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
| GSM8K | — | 20.6% |

## Knowledge

- Gemma 3 27B: 25.4 (#256)
- Llama 13b: —

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1303 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |

## Multimodal

- Gemma 3 27B: 32.0 (#94)
- Llama 13b: —

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| LMArena Vision | 1165 | — |
| GeoBench | 52% | — |
| ScienceQA | — | 43.3% |

## Multilingual

- Gemma 3 27B: 47.0 (#150)
- Llama 13b: 16.8 (#292)

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| LMArena Non-English | 1334 | 819 |
| LMArena Chinese | 1347 | — |
| LMArena French | 1368 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
| LMArena Russian | 1349 | — |
| LMArena Spanish | 1348 | — |

## Instruction Following

- Gemma 3 27B: 70.8 (#155)
- Llama 13b: 36.9 (#300)

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1321 | 781 |
| LiveBench Instruction Following | 74.9% | — |

## Long Context

- Gemma 3 27B: 27.6 (#288)
- Llama 13b: —

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| Fiction.LiveBench | 33.3% | — |
| LMArena Longer Query | 1333 | — |

## Writing & Preference

- Gemma 3 27B: 52.7 (#161)
- Llama 13b: 13.9 (#307)

| Benchmark | Gemma 3 27B | Llama 13b |
|---|---|---|
| LMArena Text | 1358 | 834 |
| LMArena Creative Writing | 1346 | 794 |
| LMArena Multi-Turn | 1344 | 753 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |

## FAQ

### Is Gemma 3 27B better than Llama 13b?

Gemma 3 27B is the stronger model overall, scoring 30.5 to 23.9 on the Noometry Index.

### Is Gemma 3 27B or Llama 13b better for coding?

Gemma 3 27B scores higher on coding benchmarks: 22.1 versus 20.9 in the Noometry coding category.

### How many benchmarks do Gemma 3 27B and Llama 13b share?

9 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Llama 13b has 21.