# Llama 3-8B vs Wizardlm 13b

> Wizardlm 13b is the stronger model overall, scoring 30.8 to 25.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-8b-vs-wizardlm-13b
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Llama 3-8B scores higher in 5 categories and Wizardlm 13b in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Wizardlm 13b leads 27.8 to 8.3.

## Snapshot

| | Llama 3-8B | Wizardlm 13b |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 25.3 | 30.8 |
| Rank | 338 | 272 |
| Context | 8K | — |
| Input $/M | $0.14 | — |
| Output $/M | $0.14 | — |
| Weights | Open | Open |

## Coding

- Llama 3-8B: 30.5 (#285)
- Wizardlm 13b: 29.6 (#293)

| Benchmark | Llama 3-8B | Wizardlm 13b |
|---|---|---|
| LMArena Coding | 1152 | 1035 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |

## Reasoning

- Llama 3-8B: 13.8 (#321)
- Wizardlm 13b: 18.5 (#265)

| Benchmark | Llama 3-8B | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1018 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.33 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |

## Math

- Llama 3-8B: 8.3 (#317)
- Wizardlm 13b: 27.8 (#235)

| Benchmark | Llama 3-8B | Wizardlm 13b |
|---|---|---|
| LMArena Math | 1151 | 1017 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |

## Knowledge

- Llama 3-8B: 7.8 (#303)
- Wizardlm 13b: —

| Benchmark | Llama 3-8B | Wizardlm 13b |
|---|---|---|
| GPQA Diamond | 26.1% | — |
| LMArena Expert | 1113 | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |

## Multilingual

- Llama 3-8B: 31.0 (#256)
- Wizardlm 13b: 27.3 (#272)

| Benchmark | Llama 3-8B | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | 1098 | 1034 |
| LMArena Chinese | 1076 | 1023 |
| LMArena French | 1158 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1003 | — |
| LMArena Russian | 1109 | — |
| LMArena Spanish | 1172 | — |

## Instruction Following

- Llama 3-8B: 58.7 (#255)
- Wizardlm 13b: 53.7 (#280)

| Benchmark | Llama 3-8B | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | 1127 | 1049 |

## Long Context

- Llama 3-8B: 34.2 (#246)
- Wizardlm 13b: 32.0 (#268)

| Benchmark | Llama 3-8B | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | 1128 | 1054 |

## Writing & Preference

- Llama 3-8B: 37.7 (#251)
- Wizardlm 13b: 30.7 (#282)

| Benchmark | Llama 3-8B | Wizardlm 13b |
|---|---|---|
| LMArena Text | 1166 | 1077 |
| LMArena Creative Writing | 1150 | 1090 |
| LMArena Multi-Turn | 1152 | 1047 |

## FAQ

### Is Llama 3-8B better than Wizardlm 13b?

Wizardlm 13b is the stronger model overall, scoring 30.8 to 25.3 on the Noometry Index.

### Is Llama 3-8B or Wizardlm 13b better for coding?

They score almost the same on coding (30.5 vs 29.6); test both on your own repository before choosing.

### How many benchmarks do Llama 3-8B and Wizardlm 13b share?

10 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Wizardlm 13b has 10.