# Gemma 2B vs Llama 3.1-405B

> Llama 3.1-405B is the stronger model overall, scoring 30.4 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2b-vs-llama-3-1-405b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemma 2B scores higher in 2 categories and Llama 3.1-405B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Llama 3.1-405B leads 40.9 to 23.1.

## Snapshot

| | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 29.1 | 30.4 |
| Rank | 305 | 279 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Gemma 2B: 28.9 (#300)
- Llama 3.1-405B: 32.7 (#257)

| Benchmark | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1010 | 1291 |
| WeirdML | — | 21.4% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |

## Agentic & Tool Use

- Gemma 2B: —
- Llama 3.1-405B: 20.9 (#131)

| Benchmark | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |

## Reasoning

- Gemma 2B: 17.9 (#275)
- Llama 3.1-405B: 16.4 (#293)

| Benchmark | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1270 |
| BIG-Bench Hard | 35.2% | 82.9% |
| Epoch Capabilities Index | 93.57 | 128.76 |
| HellaSwag | 71.4% | 89.2% |
| PIQA | 77.3% | 85.9% |
| WinoGrande | 65.4% | 89.2% |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| DTBench | — | 61.4% |
| ForecastBench | — | 59.9 |

## Math

- Gemma 2B: 27.6 (#237)
- Llama 3.1-405B: 17.3 (#283)

| Benchmark | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1009 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
| GSM8K | 17.7% | — |

## Knowledge

- Gemma 2B: —
- Llama 3.1-405B: 30.4 (#221)

| Benchmark | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | 95.3% |
| MMLU | 42.3% | 84.5% |
| TriviaQA | 53.2% | 82.7% |
| GPQA Diamond | — | 50.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| LMArena Expert | — | 1243 |
| BoolQ | 69.4% | — |

## Multilingual

- Gemma 2B: 23.1 (#289)
- Llama 3.1-405B: 40.9 (#209)

| Benchmark | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 958 | 1248 |
| LMArena Chinese | 986 | 1242 |
| LMArena Russian | 937 | 1265 |
| LMArena French | — | 1278 |
| LMArena German | — | 1252 |
| LMArena Japanese | — | 1208 |
| LMArena Korean | — | 1184 |
| LMArena Spanish | — | 1259 |

## Instruction Following

- Gemma 2B: 48.8 (#297)
- Llama 3.1-405B: 66.1 (#209)

| Benchmark | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 971 | 1259 |
| IFEval | — | 81.1% |

## Long Context

- Gemma 2B: 29.9 (#286)
- Llama 3.1-405B: 38.4 (#192)

| Benchmark | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 981 | 1266 |

## Writing & Preference

- Gemma 2B: 24.1 (#303)
- Llama 3.1-405B: 39.1 (#246)

| Benchmark | Gemma 2B | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1002 | 1284 |
| LMArena Creative Writing | 986 | 1262 |
| LMArena Multi-Turn | 945 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |

## FAQ

### Is Gemma 2B better than Llama 3.1-405B?

Llama 3.1-405B is the stronger model overall, scoring 30.4 to 29.1 on the Noometry Index.

### Is Gemma 2B or Llama 3.1-405B better for coding?

Llama 3.1-405B scores higher on coding benchmarks: 32.7 versus 28.9 in the Noometry coding category.

### How many benchmarks do Gemma 2B and Llama 3.1-405B share?

19 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Llama 3.1-405B has 42.