# Magistral Medium vs Qwen3.7 Max

> Qwen3.7 Max is the stronger model overall, scoring 51.4 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-qwen3-7-max
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Max leads 48.4 to 8.7.
- The biggest single-benchmark swing is CritPt: 0.3% for Magistral Medium and 13.4% for Qwen3.7 Max.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 51.4 |
| Rank | 224 | 35 |
| Context | 128K | 1M |
| Input $/M | $2 | $2.50 |
| Output $/M | $5 | $7.50 |
| Weights | Open | Proprietary |

## Coding

- Magistral Medium: 38.6 (#161)
- Qwen3.7 Max: 50.2 (#43)

| Benchmark | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| SciCode | 39.2% | 48.8% |
| LMArena Coding | 1319 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| ALE-Bench | — | 1,189 |

## Agentic & Tool Use

- Magistral Medium: —
- Qwen3.7 Max: 21.8 (#129)

| Benchmark | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Qwen3.7 Max: 48.4 (#36)

| Benchmark | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| CritPt | 0.3% | 13.4% |
| LMArena Hard Prompts | 1267 | 1483 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 70.4% |
| Kagi LLM Benchmark | 16.2% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 6.1% | — |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.74 |

## Math

- Magistral Medium: 32.4 (#187)
- Qwen3.7 Max: 62.3 (#26)

| Benchmark | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1249 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Qwen3.7 Max: 61.7 (#24)

| Benchmark | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1222 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Qwen3.7 Max: 57.1 (#13)

| Benchmark | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1232 | 1475 |
| LMArena Chinese | 1225 | 1533 |
| LMArena Russian | 1224 | 1482 |
| LMArena French | 1268 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1176 | — |
| LMArena Korean | 1125 | — |
| LMArena Spanish | 1269 | — |

## Instruction Following

- Magistral Medium: 66.2 (#207)
- Qwen3.7 Max: 76.9 (#34)

| Benchmark | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1254 | 1460 |

## Long Context

- Magistral Medium: 39.3 (#178)
- Qwen3.7 Max: 45.4 (#34)

| Benchmark | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1295 | 1484 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Qwen3.7 Max: 65.2 (#52)

| Benchmark | Magistral Medium | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1255 | 1476 |
| LMArena Creative Writing | 1245 | 1450 |
| LMArena Multi-Turn | 1275 | 1482 |
| EQ-Bench 4 | — | 1110 |

## FAQ

### Is Magistral Medium better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.4 to 34.8 on the Noometry Index.

### Which is cheaper, Magistral Medium or Qwen3.7 Max?

Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

### Is Magistral Medium or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 38.6 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Max does, with 1M tokens against 128K.

### How many benchmarks do Magistral Medium and Qwen3.7 Max share?

14 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen3.7 Max has 33.