# Llama 13b vs Llama 3.1-70B

> Llama 3.1-70B is the stronger model overall, scoring 29.4 to 23.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-13b-vs-llama-3-1-70b
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Llama 13b scores higher in 1 category and Llama 3.1-70B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3.1-70B leads 65.5 to 36.9.

## Snapshot

| | Llama 13b | Llama 3.1-70B |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 23.9 | 29.4 |
| Rank | 344 | 299 |
| Context | — | 128K |
| Input $/M | — | $0.40 |
| Output $/M | — | $0.40 |
| Weights | Open | Open |

## Coding

- Llama 13b: 20.9 (#332)
- Llama 3.1-70B: 29.8 (#292)

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| LMArena Coding | 683 | 1260 |
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 54.8% |

## Agentic & Tool Use

- Llama 13b: —
- Llama 3.1-70B: 24.9 (#104)

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |

## Reasoning

- Llama 13b: 13.4 (#327)
- Llama 3.1-70B: 20.8 (#215)

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1241 |
| Epoch Capabilities Index | 100.09 | 125.91 |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
| BIG-Bench Hard | 37.9% | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |

## Math

- Llama 13b: 24.4 (#259)
- Llama 3.1-70B: 12.7 (#298)

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| LMArena Math | 838 | 1252 |
| OTIS Mock AIME 2024-2025 | — | 3.6% |
| Omni-MATH | — | 21% |
| MATH Level 5 | — | 36.7% |
| GSM8K | 20.6% | — |

## Knowledge

- Llama 13b: —
- Llama 3.1-70B: 24.1 (#264)

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| MMLU | 47.7% | 80.1% |
| GPQA Diamond | — | 44.2% |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1209 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |

## Multimodal

- Llama 13b: —
- Llama 3.1-70B: —

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| ScienceQA | 43.3% | — |

## Multilingual

- Llama 13b: 16.8 (#292)
- Llama 3.1-70B: 38.9 (#220)

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 819 | 1219 |
| LMArena Chinese | — | 1215 |
| LMArena French | — | 1260 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1132 |
| LMArena Korean | — | 1140 |
| LMArena Russian | — | 1234 |
| LMArena Spanish | — | 1253 |

## Instruction Following

- Llama 13b: 36.9 (#300)
- Llama 3.1-70B: 65.5 (#218)

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 781 | 1231 |
| IFEval | — | 82.1% |

## Long Context

- Llama 13b: —
- Llama 3.1-70B: 37.6 (#208)

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | — | 1241 |

## Writing & Preference

- Llama 13b: 13.9 (#307)
- Llama 3.1-70B: 35.6 (#262)

| Benchmark | Llama 13b | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 834 | 1261 |
| LMArena Creative Writing | 794 | 1232 |
| LMArena Multi-Turn | 753 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |

## FAQ

### Is Llama 13b better than Llama 3.1-70B?

Llama 3.1-70B is the stronger model overall, scoring 29.4 to 23.9 on the Noometry Index.

### Is Llama 13b or Llama 3.1-70B better for coding?

Llama 3.1-70B scores higher on coding benchmarks: 29.8 versus 20.9 in the Noometry coding category.

### How many benchmarks do Llama 13b and Llama 3.1-70B share?

10 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Llama 3.1-70B has 35.