# Llama 3.1-405B vs Magistral Medium

> Magistral Medium is the stronger model overall, scoring 35.2 to 30.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-1-405b-vs-magistral-medium
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Llama 3.1-405B scores higher in 2 categories and Magistral Medium in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 18.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 45% for Llama 3.1-405B and 16.2% for Magistral Medium.

## Snapshot

| | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.7 | 35.2 |
| Rank | 288 | 227 |
| Context | — | 262K |
| Input $/M | — | $2 |
| Output $/M | — | $5 |
| Weights | Open | Open |

## Coding

- Llama 3.1-405B: 33.1 (#262)
- Magistral Medium: 39.1 (#161)

| Benchmark | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| LMArena Coding | 1291 | 1319 |
| SciCode | — | 39.2% |
| WeirdML | 21.4% | — |

## Agentic & Tool Use

- Llama 3.1-405B: 21.0 (#140)
- Magistral Medium: —

| Benchmark | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |

## Reasoning

- Llama 3.1-405B: 16.8 (#300)
- Magistral Medium: 8.6 (#348)

| Benchmark | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 45% | 16.2% |
| LMArena Hard Prompts | 1269 | 1267 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 23% | — |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |

## Math

- Llama 3.1-405B: 18.4 (#290)
- Magistral Medium: 35.1 (#189)

| Benchmark | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| LMArena Math | 1281 | 1250 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |

## Knowledge

- Llama 3.1-405B: 30.4 (#227)
- Magistral Medium: 33.5 (#202)

| Benchmark | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| LMArena Expert | 1243 | 1223 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |

## Multilingual

- Llama 3.1-405B: 40.7 (#214)
- Magistral Medium: 39.6 (#224)

| Benchmark | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1248 | 1232 |
| LMArena Chinese | 1242 | 1227 |
| LMArena French | 1279 | 1267 |
| LMArena German | 1252 | 1248 |
| LMArena Japanese | 1208 | 1175 |
| LMArena Korean | 1184 | 1125 |
| LMArena Russian | 1265 | 1224 |
| LMArena Spanish | 1260 | 1271 |

## Instruction Following

- Llama 3.1-405B: 65.9 (#214)
- Magistral Medium: 66.0 (#211)

| Benchmark | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1259 | 1254 |
| IFEval | 81.1% | — |

## Long Context

- Llama 3.1-405B: 38.4 (#197)
- Magistral Medium: 39.3 (#183)

| Benchmark | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1266 | 1295 |

## Writing & Preference

- Llama 3.1-405B: 38.9 (#251)
- Magistral Medium: 46.3 (#219)

| Benchmark | Llama 3.1-405B | Magistral Medium |
|---|---|---|
| LMArena Text | 1284 | 1255 |
| LMArena Creative Writing | 1262 | 1245 |
| LMArena Multi-Turn | 1297 | 1275 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |

## FAQ

### Is Llama 3.1-405B better than Magistral Medium?

Magistral Medium is the stronger model overall, scoring 35.2 to 30.7 on the Noometry Index.

### Is Llama 3.1-405B or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 33.1 in the Noometry coding category.

### How many benchmarks do Llama 3.1-405B and Magistral Medium share?

18 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Magistral Medium has 22.