# Llama 3.2 90B vs Mistral

> Mistral is the stronger model overall, scoring 29.4 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-90b-vs-mistral
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Mistral leads 20.5 to 10.4.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 3.2 90B | Mistral |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.1 | 29.4 |
| Rank | 326 | 297 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Llama 3.2 90B: —
- Mistral: 33.2 (#249)

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| LMArena Coding | — | 1162 |

## Agentic & Tool Use

- Llama 3.2 90B: 29.7 (#73)
- Mistral: —

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| BALROG | 27.3% | — |

## Reasoning

- Llama 3.2 90B: 20.9 (#207)
- Mistral: 21.3 (#199)

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1149 |
| Epoch Capabilities Index | 125.5 | — |

## Math

- Llama 3.2 90B: 10.4 (#302)
- Mistral: 20.5 (#275)

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| Omni-MATH | — | 7.2% |
| LMArena Math | — | 1180 |
| MATH Level 5 | 39.4% | — |

## Knowledge

- Llama 3.2 90B: 21.7 (#269)
- Mistral: 16.3 (#283)

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| GPQA Diamond | 41% | — |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
| MMLU | 80.3% | — |

## Multimodal

- Llama 3.2 90B: 24.9 (#119)
- Mistral: —

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |

## Multilingual

- Llama 3.2 90B: —
- Mistral: 33.0 (#249)

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| LMArena Non-English | — | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1179 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1012 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |

## Instruction Following

- Llama 3.2 90B: —
- Mistral: 52.9 (#283)

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| IFEval | — | 56.8% |
| LMArena Instruction Following | — | 1152 |

## Long Context

- Llama 3.2 90B: —
- Mistral: 35.0 (#240)

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1154 |

## Writing & Preference

- Llama 3.2 90B: —
- Mistral: 37.2 (#255)

| Benchmark | Llama 3.2 90B | Mistral |
|---|---|---|
| LMArena Text | — | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |

## FAQ

### Is Llama 3.2 90B better than Mistral?

Mistral is the stronger model overall, scoring 29.4 to 27.1 on the Noometry Index.

### How many benchmarks do Llama 3.2 90B and Mistral share?

0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Mistral has 22.