# Magistral Small vs Qwen2.5 72B Instruct

> Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 30.2 on the Noometry Index. Magistral Small costs 3.3× less per token, which makes it the better buy when Qwen2.5 72B Instruct's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/magistral-small-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Magistral Small scores higher in 3 categories and Qwen2.5 72B Instruct in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2.5 72B Instruct leads 22.3 to 6.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 30% for Magistral Small and 8.1% for Qwen2.5 72B Instruct.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 128K.

## Snapshot

| | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.2 | 31.9 |
| Rank | 296 | 267 |
| Context | 128K | 131K |
| Input $/M | $0.50 | $1.40 |
| Output $/M | $1.50 | $5.60 |
| Weights | Open | Open |

## Coding

- Magistral Small: 38.4 (#176)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| SciCode | 35.2% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LMArena Coding | — | 1292 |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Magistral Small: —
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Magistral Small: 6.8 (#350)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| DTBench | 61.3% | 62.9% |
| Epoch Capabilities Index | 133.19 | 129 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| ARC-AGI-1 | 5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 3% | — |
| LMArena Hard Prompts | — | 1271 |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Magistral Small: 26.2 (#261)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Magistral Small: 30.9 (#223)
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 56.1% | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Magistral Small: —
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1256 |

## Instruction Following

- Magistral Small: —
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | — | 80.6% |
| LMArena Instruction Following | — | 1254 |

## Long Context

- Magistral Small: —
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |

## Writing & Preference

- Magistral Small: —
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | Magistral Small | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | — | 1269 |
| LMArena Creative Writing | — | 1221 |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |

## FAQ

### Is Magistral Small better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 30.2 on the Noometry Index. Magistral Small costs 3.3× less per token, which makes it the better buy when Qwen2.5 72B Instruct's lead doesn't matter for your workload.

### Which is cheaper, Magistral Small or Qwen2.5 72B Instruct?

Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

### Is Magistral Small or Qwen2.5 72B Instruct better for coding?

Magistral Small scores higher on coding benchmarks: 38.4 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen2.5 72B Instruct does, with 131K tokens against 128K.

### How many benchmarks do Magistral Small and Qwen2.5 72B Instruct share?

4 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Qwen2.5 72B Instruct has 43.