# Magistral Medium vs Qwen2-72B

> Magistral Medium is the stronger model overall, scoring 34.8 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Magistral Medium scores higher in 7 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2-72B leads 22.2 to 8.7.

## Snapshot

| | Magistral Medium | Qwen2-72B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 29.5 |
| Rank | 224 | 294 |
| Context | 128K | — |
| Input $/M | $2 | — |
| Output $/M | $5 | — |
| Weights | Open | Open |

## Coding

- Magistral Medium: 38.6 (#161)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1319 | 1196 |
| SciCode | 39.2% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Magistral Medium: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1191 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| Epoch Capabilities Index | — | 125.27 |

## Math

- Magistral Medium: 32.4 (#187)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Math | 1249 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1222 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1232 | 1176 |
| LMArena Chinese | 1225 | 1240 |
| LMArena French | 1268 | 1169 |
| LMArena German | 1248 | 1151 |
| LMArena Japanese | 1176 | 1111 |
| LMArena Korean | 1125 | 1083 |
| LMArena Russian | 1224 | 1169 |
| LMArena Spanish | 1269 | 1168 |

## Instruction Following

- Magistral Medium: 66.2 (#207)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1181 |

## Long Context

- Magistral Medium: 39.3 (#178)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1295 | 1193 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Text | 1255 | 1203 |
| LMArena Creative Writing | 1245 | 1181 |
| LMArena Multi-Turn | 1275 | 1195 |

## FAQ

### Is Magistral Medium better than Qwen2-72B?

Magistral Medium is the stronger model overall, scoring 34.8 to 29.5 on the Noometry Index.

### Is Magistral Medium or Qwen2-72B better for coding?

Magistral Medium scores higher on coding benchmarks: 38.6 versus 28.7 in the Noometry coding category.

### How many benchmarks do Magistral Medium and Qwen2-72B share?

17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen2-72B has 26.