# Llama 2-70B vs Magistral Medium

> Magistral Medium is the stronger model overall, scoring 34.8 to 24.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-70b-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Llama 2-70B scores higher in 1 category and Magistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Magistral Medium leads 32.9 to 7.4.

## Snapshot

| | Llama 2-70B | Magistral Medium |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.1 | 34.8 |
| Rank | 343 | 224 |
| Context | — | 128K |
| Input $/M | — | $2 |
| Output $/M | — | $5 |
| Weights | Open | Open |

## Coding

- Llama 2-70B: 30.8 (#281)
- Magistral Medium: 38.6 (#161)

| Benchmark | Llama 2-70B | Magistral Medium |
|---|---|---|
| LMArena Coding | 1079 | 1319 |
| SciCode | — | 39.2% |

## Reasoning

- Llama 2-70B: 13.7 (#324)
- Magistral Medium: 8.7 (#342)

| Benchmark | Llama 2-70B | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.59 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |

## Math

- Llama 2-70B: 7.5 (#320)
- Magistral Medium: 32.4 (#187)

| Benchmark | Llama 2-70B | Magistral Medium |
|---|---|---|
| LMArena Math | 1091 | 1249 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |

## Knowledge

- Llama 2-70B: 7.4 (#305)
- Magistral Medium: 32.9 (#199)

| Benchmark | Llama 2-70B | Magistral Medium |
|---|---|---|
| LMArena Expert | 1039 | 1222 |
| GPQA Diamond | 26.3% | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |

## Multilingual

- Llama 2-70B: 27.9 (#269)
- Magistral Medium: 39.8 (#219)

| Benchmark | Llama 2-70B | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1045 | 1232 |
| LMArena Chinese | 994 | 1225 |
| LMArena French | 1089 | 1268 |
| LMArena German | 1041 | 1248 |
| LMArena Japanese | 927 | 1176 |
| LMArena Korean | 964 | 1125 |
| LMArena Russian | 1083 | 1224 |
| LMArena Spanish | 1142 | 1269 |

## Instruction Following

- Llama 2-70B: 55.1 (#273)
- Magistral Medium: 66.2 (#207)

| Benchmark | Llama 2-70B | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1071 | 1254 |

## Long Context

- Llama 2-70B: 32.2 (#265)
- Magistral Medium: 39.3 (#178)

| Benchmark | Llama 2-70B | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1062 | 1295 |

## Writing & Preference

- Llama 2-70B: 32.5 (#274)
- Magistral Medium: 46.5 (#214)

| Benchmark | Llama 2-70B | Magistral Medium |
|---|---|---|
| LMArena Text | 1115 | 1255 |
| LMArena Creative Writing | 1075 | 1245 |
| LMArena Multi-Turn | 1088 | 1275 |

## FAQ

### Is Llama 2-70B better than Magistral Medium?

Magistral Medium is the stronger model overall, scoring 34.8 to 24.1 on the Noometry Index.

### Is Llama 2-70B or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 38.6 versus 30.8 in the Noometry coding category.

### How many benchmarks do Llama 2-70B and Magistral Medium share?

17 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Magistral Medium has 22.