# Llama 2-7B vs Llama 3.1-8B

> Llama 2-7B is the stronger model overall, scoring 28.6 to 22.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-7b-vs-llama-3-1-8b
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Llama 2-7B scores higher in 4 categories and Llama 3.1-8B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-7B leads 27.7 to 8.0.

## Snapshot

| | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 28.6 | 22.8 |
| Rank | 315 | 347 |
| Context | — | 128K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- Llama 2-7B: 28.7 (#302)
- Llama 3.1-8B: 19.9 (#335)

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| LMArena Coding | 1002 | 1195 |
| SciCode | — | 13.2% |
| WeirdML | — | 1.7% |
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 40.5% |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |

## Agentic & Tool Use

- Llama 2-7B: —
- Llama 3.1-8B: 22.3 (#123)

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 25.8% |
| BALROG | — | 15.1% |

## Reasoning

- Llama 2-7B: 15.1 (#309)
- Llama 3.1-8B: 14.5 (#316)

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1009 | 1175 |
| Epoch Capabilities Index | 98.54 | 116.48 |
| PIQA | 78.8% | 81.2% |
| CritPt | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 5.4% |
| BIG-Bench Hard | 39.2% | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| WinoGrande | 69.2% | — |

## Math

- Llama 2-7B: 28.2 (#231)
- Llama 3.1-8B: 9.5 (#311)

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| LMArena Math | 1042 | 1179 |
| GSM8K | 16.7% | 82.4% |
| OTIS Mock AIME 2024-2025 | — | 1.7% |
| Omni-MATH | — | 13.7% |
| MATH Level 5 | — | 22.9% |

## Knowledge

- Llama 2-7B: 27.7 (#243)
- Llama 3.1-8B: 8.0 (#302)

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| LMArena Expert | 1036 | 1144 |
| BoolQ | 77.9% | 82.8% |
| MMLU | 45.8% | 56.1% |
| GPQA Diamond | — | 27% |
| MMLU-Pro | — | 40.6% |
| GPQA (HELM) | — | 24.7% |
| ARC (AI2) Challenge | 45.9% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |

## Multimodal

- Llama 2-7B: —
- Llama 3.1-8B: —

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| ScienceQA | 43.1% | — |

## Multilingual

- Llama 2-7B: 23.9 (#288)
- Llama 3.1-8B: 34.2 (#244)

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 973 | 1148 |
| LMArena Chinese | 973 | 1151 |
| LMArena French | 969 | 1176 |
| LMArena German | 978 | 1144 |
| LMArena Russian | 995 | 1158 |
| LMArena Spanish | 1007 | 1169 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1053 |

## Instruction Following

- Llama 2-7B: 51.0 (#293)
- Llama 3.1-8B: 59.1 (#253)

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| LMArena Instruction Following | 1006 | 1159 |
| IFEval | — | 74.3% |

## Long Context

- Llama 2-7B: 30.4 (#282)
- Llama 3.1-8B: 35.8 (#233)

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 999 | 1182 |

## Writing & Preference

- Llama 2-7B: 28.1 (#293)
- Llama 3.1-8B: 29.9 (#285)

| Benchmark | Llama 2-7B | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1053 | 1187 |
| LMArena Creative Writing | 1033 | 1154 |
| LMArena Multi-Turn | 1029 | 1172 |
| EQ-Bench Creative Writing | — | 713 |
| WildBench | — | 68.7% |

## FAQ

### Is Llama 2-7B better than Llama 3.1-8B?

Llama 2-7B is the stronger model overall, scoring 28.6 to 22.8 on the Noometry Index.

### Is Llama 2-7B or Llama 3.1-8B better for coding?

Llama 2-7B scores higher on coding benchmarks: 28.7 versus 19.9 in the Noometry coding category.

### How many benchmarks do Llama 2-7B and Llama 3.1-8B share?

21 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Llama 3.1-8B has 43.