# Magistral Medium vs Mistral Small 3.1

> Magistral Medium is the stronger model overall, scoring 34.8 to 31.4 on the Noometry Index. Mistral Small 3.1 costs 6.8× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-mistral-small-3-1
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Magistral Medium scores higher in 5 categories and Mistral Small 3.1 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 32.4 to 13.7.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $2 / $5 for Magistral Medium.

## Snapshot

| | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 34.8 | 31.4 |
| Rank | 224 | 263 |
| Context | 128K | 128K |
| Input $/M | $2 | $0.35 |
| Output $/M | $5 | $0.56 |
| Weights | Open | Open |

## Coding

- Magistral Medium: 38.6 (#161)
- Mistral Small 3.1: 37.7 (#175)

| Benchmark | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1319 | 1309 |
| SciCode | 39.2% | — |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Mistral Small 3.1: 18.9 (#249)

| Benchmark | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1278 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 1% |
| Epoch Capabilities Index | — | 127.48 |

## Math

- Magistral Medium: 32.4 (#187)
- Mistral Small 3.1: 13.7 (#295)

| Benchmark | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Math | 1249 | 1261 |
| OTIS Mock AIME 2024-2025 | — | 3.9% |
| Omni-MATH | — | 24.8% |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Mistral Small 3.1: 22.6 (#266)

| Benchmark | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Expert | 1222 | 1258 |
| GPQA Diamond | — | 41.9% |
| MMLU-Pro | — | 61% |
| GPQA (HELM) | — | 39.2% |

## Multimodal

- Magistral Medium: —
- Mistral Small 3.1: 32.6 (#93)

| Benchmark | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Mistral Small 3.1: 41.4 (#204)

| Benchmark | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1232 | 1255 |
| LMArena Chinese | 1225 | 1254 |
| LMArena French | 1268 | 1270 |
| LMArena German | 1248 | 1266 |
| LMArena Japanese | 1176 | 1210 |
| LMArena Korean | 1125 | 1206 |
| LMArena Russian | 1224 | 1263 |
| LMArena Spanish | 1269 | 1283 |

## Instruction Following

- Magistral Medium: 66.2 (#207)
- Mistral Small 3.1: 63.8 (#225)

| Benchmark | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1264 |
| IFEval | — | 75% |

## Long Context

- Magistral Medium: 39.3 (#178)
- Mistral Small 3.1: 39.5 (#172)

| Benchmark | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1295 | 1300 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Mistral Small 3.1: 37.2 (#254)

| Benchmark | Magistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1255 | 1278 |
| LMArena Creative Writing | 1245 | 1253 |
| LMArena Multi-Turn | 1275 | 1270 |
| EQ-Bench Creative Writing | — | 761 |
| WildBench | — | 78.8% |

## FAQ

### Is Magistral Medium better than Mistral Small 3.1?

Magistral Medium is the stronger model overall, scoring 34.8 to 31.4 on the Noometry Index. Mistral Small 3.1 costs 6.8× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.

### Which is cheaper, Magistral Medium or Mistral Small 3.1?

Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Magistral Medium lists at $2 and $5.

### Is Magistral Medium or Mistral Small 3.1 better for coding?

They score almost the same on coding (38.6 vs 37.7); test both on your own repository before choosing.

### Which has the bigger context window?

Both accept 128K tokens.

### How many benchmarks do Magistral Medium and Mistral Small 3.1 share?

17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Mistral Small 3.1 has 28.